library(data.table)
library(clusterProfiler)
library(dplyr)
library(Seurat)
library(ggplot2)
library(circlize)

library(org.Hs.eg.db)
library(msigdbr)

Loading required package: AnnotationDbi

Loading required package: stats4

Loading required package: BiocGenerics


Attaching package: ‘BiocGenerics’


The following object is masked from ‘package:SeuratObject’:

    intersect


The following objects are masked from ‘package:dplyr’:

    combine, intersect, setdiff, union


The following objects are masked from ‘package:stats’:

    IQR, mad, sd, var, xtabs


The following objects are masked from ‘package:base’:

    anyDuplicated, aperm, append, as.data.frame, basename, cbind,
    colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,
    get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,
    match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,
    Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,
    table, tapply, union, unique, unsplit, which.max, which.min


Loading required package: Biobase

Welcome to Bioconductor

    Vignettes contain introductory material; view with
    'browseVignettes()'. To cite Bioconductor, see
    'citation("Biobase")', and for packages 'citation("pkgname")'.


Loading required package: IRanges

Loading required package: S4Vectors


Attaching package: ‘S4Vectors’


The following objects are masked from ‘package:dplyr’:

    first, rename


The following object is masked from ‘package:clusterProfiler’:

    rename


The following objects are masked from ‘package:data.table’:

    first, second


The following object is masked from ‘package:utils’:

    findMatches


The following objects are masked from ‘package:base’:

    expand.grid, I, unname


Attaching package: ‘IRanges’


The following object is masked from ‘package:sp’:

    %over%


The following objects are masked from ‘package:dplyr’:

    collapse, desc, slice


The following object is masked from ‘package:clusterProfiler’:

    slice


The following object is masked from ‘package:data.table’:

    shift


Attaching package: ‘AnnotationDbi’


The following object is masked from ‘package:dplyr’:

    select


The following object is masked from ‘package:clusterProfiler’:

    select

m_t2g <- msigdbr(species = "Homo sapiens", category = "H") %>% 
  dplyr::select(gs_name, entrez_gene)
head(m_t2g)

fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/main_PC9_LUNG_run10_t0_t14_cyc/all_driver_types_match_counts.csv')

fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/main_PC9_LUNG_run10_t0_t14_cyc/driver_summary_shap_total.csv')

fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/main_PC9_LUNG_run10_t0_t14_cyc/driver_summary_grad_total.csv')

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t0_t14_cyc'
read_dir <- file.path(read_dir,run_name)

drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(drivers)

gene <- bitr(drivers$V1, fromType="SYMBOL", toType=c("UNIPROT","ENTREZID"), OrgDb="org.Hs.eg.db")

'select()' returned 1:many mapping between keys and columns

Warning message in bitr(drivers$V1, fromType = "SYMBOL", toType = c("UNIPROT", "ENTREZID"), :
“6.35% of input gene IDs are fail to map...”

go <- enrichGO(gene     = ![本地路径](20200327_1.png "相对路径演示"),
              OrgDb        = org.Hs.eg.db,
              keyType       = 'ENTREZID',
              ont          = "BP",
              minGSSize    = 0,
              #maxGSSize    = 500,
              pvalueCutoff = 1,
              qvalueCutoff = 1,
              #eps = eps,
              #verbose      = FALSE
              )

go@result

ggo <- groupGO(gene     = gene$ENTREZID,
               OrgDb    = org.Hs.eg.db,
               keyType       = 'ENTREZID',
               ont      = "BP",
               #level    = 3,
               readable = TRUE)

ggo@result

drivers_ann <- merge(x=gene,y=drivers,by.x = 'SYMBOL',by.y = 'V1',all = F)

weight <- drivers_ann$weight_shap_total_mean
names(weight) <- drivers_ann$ENTREZID
weight <- weight[order(weight,decreasing = T)]

gsego <- gseGO(gene     = weight,
              OrgDb        = org.Hs.eg.db,
              keyType       = 'ENTREZID',
              ont          = "BP",
              minGSSize    = 0,
              #maxGSSize    = 500,
              pvalueCutoff = 1,
              #qvalueCutoff = 1,
              #eps = eps,
              #verbose      = FALSE
              )

preparing geneSet collections...

GSEA analysis...

Warning message in preparePathwaysAndStats(pathways, stats, minSize, maxSize, gseaParam, :
“There are ties in the preranked stats (53.91% of the list).
The order of those tied genes will be arbitrary, which may produce unexpected results.”
Warning message in preparePathwaysAndStats(pathways, stats, minSize, maxSize, gseaParam, :
“There are duplicate gene names, fgsea may produce unexpected results.”
Warning message in preparePathwaysAndStats(pathways, stats, minSize, maxSize, gseaParam, :
“All values in the stats vector are greater than zero and scoreType is "std", maybe you should switch to scoreType = "pos".”
Warning message in fgseaMultilevel(pathways = pathways, stats = stats, minSize = minSize, :
“There were 1 pathways for which P-values were not calculated properly due to unbalanced (positive and negative) gene-level statistic values. For such pathways pval, padj, NES, log2err are set to NA. You can try to increase the value of the argument nPermSimple (for example set it nPermSimple = 10000)”
leading edge analysis...

done...

gsego@result

drivers[drivers$is_tf]

drivers[drivers$is_in_FAM]

drivers[drivers$is_in_ROS]

drivers[drivers$is_in_Pathway]

drivers$rank = 1:dim(drivers)[1]

drivers[drivers$is_in_Pathway]

driver_info <- fread(file.path(read_dir,'driver_info_9.csv'))

driver_info[driver_info$is_in_Pathway]

kk <- enrichKEGG(gene         = gene$ENTREZID,
                 #keyType      = 'uniprot',
                 organism     = 'hsa',
                 pvalueCutoff = 0.1)
head(kk)

?enrichKEGG

plot(table(kk@result$subcategory))

browseKEGG(kk, 'hsa05208')

Error in browseURL(url): 'browser' must be a non-empty character string
Traceback:

1. browseKEGG(kk, "hsa05208")
2. browseURL(url)
3. stop("'browser' must be a non-empty character string")

library("pathview")

##############################################################################
Pathview is an open source software package distributed under GNU General
Public License version 3 (GPLv3). Details of GPLv3 is available at
http://www.gnu.org/licenses/gpl-3.0.html. Particullary, users are required to
formally cite the original Pathview paper (not just mention it) in publications
or products. For details, do citation("pathview") within R.

The pathview downloads and uses KEGG data. Non-academic uses may require a KEGG
license agreement (details at http://www.kegg.jp/kegg/legal.html).
##############################################################################

hsa05208 <- pathview(gene.data  = weight,
                     pathway.id = "hsa05208",
                     species    = "hsa",
                     limit      = list(gene=max(abs(weight)), cpd=1))

Info: Downloading xml files for hsa05208, 1/1 pathways..

Info: Downloading png files for hsa05208, 1/1 pathways..

'select()' returned 1:1 mapping between keys and columns

Info: Working in directory /sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master

Info: Writing image file hsa05208.pathview.png

kk@result['hsa05208',]

bngeneplot(results = kk@result, exp = vsted, pathNum = 17)

set.seed(123)
counts <- matrix(sample(1:100, 100, replace=TRUE), nrow=10, ncol=10)
numbers <- 1:10

# 将数值向量转换为字符向量
char_vector <- as.character(numbers)

library(DESeq2)
#counts = read.table("GSE133624_reads-count-all-sample.txt", header=1, row.names=1)
meta = sapply(char_vector, function (x) substring(x,1,1))
meta = data.frame(meta)
colnames(meta) = c("Condition")

dds <- DESeqDataSetFromMatrix(countData = counts,
                              colData = meta,
                              design= ~ Condition)
v = varianceStabilizingTransformation(dds, blind=FALSE)
vsted = assay(v)

Warning message in DESeqDataSet(se, design = design, ignoreRank):
“some variables in design formula are characters, converting to factors”
-- note: fitType='parametric', but the dispersion trend was not well captured by the
   function: y = a/x + b, and a local regression fit was automatically substituted.
   specify fitType='local' or 'mean' to avoid this message next time.

Warning message in lfproc(x, y, weights = weights, cens = cens, base = base, geth = geth, :
“Estimated rdf < 1.0; not estimating variance”

vsted

mtx <- drivers[,c('weight_shap_total_mean')]
#rownames(mtx) <- drivers$V1
mtx <- as.matrix(mtx)

replicated_matrix <- matrix(mtx, nrow=nrow(mtx), ncol=10, byrow=FALSE)
rownames(replicated_matrix) <- drivers$V1
colnames(replicated_matrix) <- seq(1,10)

kk

#
# over-representation test
#
#...@organism 	 hsa 
#...@ontology 	 KEGG 
#...@keytype 	 kegg 
#...@gene 	 chr [1:59] "2335" "595" "3856" "2947" "928" "9741" "4192" "5052" "5230" ...
#...pvalues adjusted by 'BH' with cutoff <0.1 
#...11 enriched terms found
'data.frame':	11 obs. of  11 variables:
 $ category   : chr  "Cellular Processes" "Cellular Processes" "Metabolism" "Human Diseases" ...
 $ subcategory: chr  "Cell growth and death" "Cell growth and death" "Carbohydrate metabolism" "Neurodegenerative disease" ...
 $ ID         : chr  "hsa04218" "hsa04110" "hsa00010" "hsa05012" ...
 $ Description: chr  "Cellular senescence" "Cell cycle" "Glycolysis / Gluconeogenesis" "Parkinson disease" ...
 $ GeneRatio  : chr  "7/49" "7/49" "4/49" "7/49" ...
 $ BgRatio    : chr  "156/8753" "157/8753" "67/8753" "266/8753" ...
 $ pvalue     : num  2.29e-05 2.38e-05 5.13e-04 6.37e-04 7.87e-04 ...
 $ p.adjust   : num  0.00172 0.00172 0.02266 0.02266 0.02266 ...
 $ qvalue     : num  0.00139 0.00139 0.01839 0.01839 0.01839 ...
 $ geneID     : chr  "595/8878/983/891/2305/3486/4605" "595/7027/983/891/5111/4172/10403" "5230/5315/3945/218" "7314/7846/10105/5694/7277/10383/7316" ...
 $ Count      : int  7 7 4 7 4 9 4 5 5 6 ...
#...Citation
 T Wu, E Hu, S Xu, M Chen, P Guo, Z Dai, T Feng, L Zhou, W Tang, L Zhan, X Fu, S Liu, X Bo, and G Yu.
 clusterProfiler 4.0: A universal enrichment tool for interpreting omics data.
 The Innovation. 2021, 2(3):100141

pway = setReadable(kk, OrgDb=org.Hs.eg.db, keyType="ENTREZID")

ttt <- bitr(drivers$V1, fromType="SYMBOL", toType=c("ENTREZID"), OrgDb="org.Hs.eg.db")
rownames(ttt) <- ttt$SYMBOL

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(drivers$V1, fromType = "SYMBOL", toType = c("ENTREZID"), :
“1.67% of input gene IDs are fail to map...”

rownames(replicated_matrix) <- ttt[rownames(replicated_matrix),'ENTREZID']

noise <- matrix(rnorm(25, mean=1, sd=1),nrow=nrow(replicated_matrix),ncol=ncol(replicated_matrix))

# 将随机噪声添加到原始矩阵
noisy_matrix <- replicated_matrix*1000 + noise

rownames(noisy_matrix) <- drivers$V1
colnames(noisy_matrix) <- seq(1,10)
rownames(noisy_matrix) <- ttt[rownames(noisy_matrix),'ENTREZID']

CBNplot::bngeneplot(results = pway, exp = noisy_matrix, expRow = 'ENTREZID',pathNum = 62)

'select()' returned 1:1 mapping between keys and columns

'select()' returned 1:1 mapping between keys and columns

no edge present in graph

which(kk@result$ID == 'hsa05208')

attributes(pway)$result

pway

#
# over-representation test
#
#...@organism 	 hsa 
#...@ontology 	 KEGG 
#...@keytype 	 ENTREZID 
#...@gene 	 chr [1:59] "2335" "595" "3856" "2947" "928" "9741" "4192" "5052" "5230" ...
#...pvalues adjusted by 'BH' with cutoff <0.1 
#...11 enriched terms found
'data.frame':	11 obs. of  11 variables:
 $ category   : chr  "Cellular Processes" "Cellular Processes" "Metabolism" "Human Diseases" ...
 $ subcategory: chr  "Cell growth and death" "Cell growth and death" "Carbohydrate metabolism" "Neurodegenerative disease" ...
 $ ID         : chr  "hsa04218" "hsa04110" "hsa00010" "hsa05012" ...
 $ Description: chr  "Cellular senescence" "Cell cycle" "Glycolysis / Gluconeogenesis" "Parkinson disease" ...
 $ GeneRatio  : chr  "7/49" "7/49" "4/49" "7/49" ...
 $ BgRatio    : chr  "156/8753" "157/8753" "67/8753" "266/8753" ...
 $ pvalue     : num  2.29e-05 2.38e-05 5.13e-04 6.37e-04 7.87e-04 ...
 $ p.adjust   : num  0.00172 0.00172 0.02266 0.02266 0.02266 ...
 $ qvalue     : num  0.00139 0.00139 0.01839 0.01839 0.01839 ...
 $ geneID     : chr  "CCND1/SQSTM1/CDK1/CCNB1/FOXM1/IGFBP3/MYBL2" "CCND1/TFDP1/CDK1/CCNB1/PCNA/MCM3/NDC80" "PGK1/PKM/LDHB/ALDH3A1" "UBB/TUBA1A/PPIF/PSMB6/TUBA4A/TUBB4B/UBC" ...
 $ Count      : int  7 7 4 7 4 9 4 5 5 6 ...
#...Citation
 T Wu, E Hu, S Xu, M Chen, P Guo, Z Dai, T Feng, L Zhou, W Tang, L Zhan, X Fu, S Liu, X Bo, and G Yu.
 clusterProfiler 4.0: A universal enrichment tool for interpreting omics data.
 The Innovation. 2021, 2(3):100141

pathway_hallmark = openxlsx::read.xlsx(file.path('./resources/pathway', 'Gene_signature_list_paper_supp.xlsx'))

pathway_hallmark

drivers = as.data.frame(drivers)
for (pw in colnames(pathway_hallmark)){
    drivers[pw] = drivers$V1 %in% pathway_hallmark[,pw]
}

drivers

drivers[drivers$HALLMARK_REACTIVE_OXYGEN_SPECIES_PATHWAY,]

drivers$rank_shap_weight = rank(-drivers$weight_shap_total_mean)
drivers$rank_grad_weight = rank(-abs(drivers$weight_grad_total_dir_mean))

drivers[drivers$is_in_ROS,]

drivers[drivers$is_in_Pathway,]

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t7_t14_cyc'
read_dir <- file.path(read_dir,run_name)

drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(drivers)

drivers$rank_shap_weight = rank(-drivers$weight_shap_total_mean)
drivers$rank_grad_weight = rank(-abs(drivers$weight_grad_total_dir_mean))

drivers[drivers$is_in_ROS,]

drivers[drivers$is_in_Pathway,]

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t14_ncyc_cyc'
read_dir <- file.path(read_dir,run_name)

drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(drivers)

drivers$rank_shap_weight = rank(-drivers$weight_shap_total_mean)
drivers$rank_grad_weight = rank(-abs(drivers$weight_grad_total_dir_mean))

drivers[drivers$is_in_ROS,]

drivers[drivers$is_in_Pathway,]

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t0_t14_cyc'
read_dir <- file.path(read_dir,run_name)

drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(drivers)

drivers$rank_shap_weight = rank(-drivers$weight_shap_total_mean)
drivers$rank_grad_weight = rank(-abs(drivers$weight_grad_total_dir_mean))

drivers[drivers$is_in_Pathway,]

tdf <- fread(file.path(read_dir,'driver_info_0.csv')) %>% dplyr::select(c('V1','weight_shap_total'))

file_name = paste0('driver_info_',0,'.csv')
df <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
for (i in 1:9){
    file_name = paste0('driver_info_',i,'.csv')
    tdf <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
    df <- merge(df,tdf,by = 'V1',all = T,suffixes=c(i,i+1))
    
}
colnames(df) <- c('Gene',paste0('run',0:9))

plot_df <- tidyr::gather(df, key = "variable", value = "value",-Gene)

plot_df

pathway_hallmark = openxlsx::read.xlsx(file.path('./resources/pathway', 'Gene_signature_list_paper_supp.xlsx'))

plot_df$pw = plot_df$Gene %in% pathway_hallmark$HALLMARK_REACTIVE_OXYGEN_SPECIES_PATHWAY

pathway_hallmark$HALLMARK_REACTIVE_OXYGEN_SPECIES_PATHWAY

pathway_hallmark$HALLMARK_FATTY_ACID_METABOLISM

ggplot(data = plot_df)+
geom_boxplot(aes(x=variable,y=value,fill=pw))+
theme_classic()

Warning message:
“Removed 408 rows containing non-finite outside the scale range
(`stat_boxplot()`).”

ggplot(data = plot_df)+
geom_violin(aes(x=variable,y=value,fill=pw))+
theme_classic()

Warning message:
“Removed 408 rows containing non-finite outside the scale range
(`stat_ydensity()`).”

plot_df$pw <- plot_df$pw %>% as.character %>% factor(levels = c('TRUE','FALSE'),labels = c('In two pathway','Out of two pathway'))

#ggplot2 | position_dodge位置调整函数https://blog.csdn.net/weixin_54000907/article/details/120108707
box_p <- ggplot(data = plot_df)+
stat_boxplot(aes(x=variable,y=value,color = pw),geom = "errorbar",linewidth=1.5,
               position = position_dodge2(padding = 0.2))+
geom_boxplot(aes(x=variable,y=value,color = pw),outliers = F,linewidth=1.5,fill='white',position = position_dodge2(padding = 0.2))+
#geom_jitter(aes(x=variable,y=value,color = pw),width = 0.15)+
theme_classic()+
xlab('Run with different seeds')+
ylab('SHAP weight of driver genes')+
labs(fill="Genes Type")+
theme_bw()+
scale_color_manual(values = c('In two pathway'= '#559073FF','Out of two pathway'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5),
    axis.title.y = element_text(vjust = 6),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(angle = 60,vjust = 0.5),
    #axis.text.y = element_text(hjust = 8),
    axis.ticks = element_line(linewidth = 1.5),
   axis.ticks.length = unit(10,'points'),
   axis.line = element_line(linewidth = 1.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   panel.border = element_blank(),
   panel.grid = element_blank(),
   #panel.grid.major.x =element_line(),
   legend.key.size = unit(20,'points'),
   legend.text = element_text(face = 'italic',size=18),
   #legend.title = element_text(face = 'bold',size=18), 
   legend.title = element_blank(),
   legend.position = 'top'
      
)
box_p

Warning message:
“Removed 408 rows containing non-finite outside the scale range
(`stat_boxplot()`).”
Warning message:
“Removed 408 rows containing non-finite outside the scale range
(`stat_boxplot()`).”

ggsave(plot = box_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_box_p.pdf',
       width =16/1.5, height =16/1.5)
ggsave(plot = box_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_box_p.png',
       width =16/1.5, height =16/1.5)

Warning message:
“Removed 408 rows containing non-finite outside the scale range
(`stat_boxplot()`).”
Warning message:
“Removed 408 rows containing non-finite outside the scale range
(`stat_boxplot()`).”
Warning message:
“Removed 408 rows containing non-finite outside the scale range
(`stat_boxplot()`).”
Warning message:
“Removed 408 rows containing non-finite outside the scale range
(`stat_boxplot()`).”

gl <- drivers[order(weight_shap_total_mean,decreasing = T),]$V1[1:10]

tmp <- plot_df[plot_df$Gene %in% gl,]

tmp$Gene <- factor(tmp$Gene,levels = rev(gl))

gl

?ggsci::scale_fill_npg()

ridge_p <- ggplot(tmp, aes(x = value, y = Gene, fill = Gene)) +
  ggridges::geom_density_ridges() +
  ggridges::theme_ridges() + 
  ggsci::scale_fill_npg()+
xlab('SHAP weight')+
ylab('Driver genes')+
ggtitle("Weight through model with different seeds")+
scale_color_manual(values = c('In two pathway'= '#559073FF','Out of two pathway'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   legend.position = 'none'
      
)
ridge_p

Picking joint bandwidth of 0.000309

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

ggsave(plot = ridge_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_ridge_p.pdf',
       width =16/1.5, height =16/1.5)
ggsave(plot = ridge_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_ridge_p.png',
       width =16/1.5, height =16/1.5)

Picking joint bandwidth of 0.000309

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”
Picking joint bandwidth of 0.000309

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

normalize <- function(v) {
  (v - min(v)) / (max(v) - min(v))
}

drivers$norm_shap <-  normalize(drivers$weight_shap_total_mean)
ddf <- drivers[order(drivers$weight_shap_total_mean,decreasing = T),][1:10,] %>% as.data.frame()
ddf$V1 <- factor(ddf$V1,levels = ddf$V1)

ggplot(ddf) +
  geom_bar(aes(x = V1, y = norm_shap),stat = "identity",fill=rgb(0.1,0.4,0.5,0.7))+
    theme_classic()

drivers$norm_shap <-  normalize(drivers$weight_shap_total_mean)
ddf <- drivers[order(drivers$weight_shap_total_mean,decreasing = T),][1:10,] %>% as.data.frame()
ddf$V1 <- factor(ddf$V1,levels = rev(ddf$V1))

bar_p <-  ggplot(ddf) +
  geom_bar(aes(x = V1, y = norm_shap,fill=norm_shap),stat = "identity",width = 0.6, alpha=1)+
    scale_fill_gradient(low = "#659999",high = "#f4791f")+
    coord_flip() +
    theme_bw()+
    ylab('SHAP weight')+
    xlab('Driver genes')+
    ggtitle("Modeling between T0 T14")+
    #scale_color_manual(values = c('In two pathway'= '#559073FF','Out of two pathway'='#D28130FF'))+
    theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5,hjust = 0.5),
        axis.title.y = element_text(vjust = 5,hjust = 0.5),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
       axis.text.x = element_text(vjust = 0.5),
       axis.text.y = element_text(colour = c(rep('black',times = 5),'#BA002B','black','#BA002B',rep('black',times = 2))),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
        panel.border = element_rect(size = 1.5),
        panel.grid = element_blank(),
        panel.grid.minor.x = element_line(linetype = 5),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(10,'points'),
       legend.position = 'none'

    )
bar_p

Warning message:
“Vectorized input to `element_text()` is not officially supported.
ℹ Results may be unexpected or may change in future versions of ggplot2.”

ggsave(plot = bar_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_bar_p.pdf',
       width =12/1.5, height =16/1.5)
ggsave(plot = bar_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_bar_p.png',
       width =12/1.5, height =16/1.5)

#R语言ggplot2图例标签、标题、顺序修改和删除https://blog.csdn.net/LeaningR/article/details/114576555
#ggplot2 美化 背景/主题（theme）https://zhuanlan.zhihu.com/p/463041897
p <- ggplot(data = plot_df)+
geom_bar(aes(x=ID,y=enrichmentScore,fill=-log10(pvalue)),stat="identity",width = 0.6, alpha=0.85)+
#ggsci::scale_fill_gsea()+
scale_fill_gradient(low = "#659999",high = "#f4791f")+
#scale_fill_gradient(low = "#8360c3",high = "#2ebf91")+
#scale_fill_gradient(low = "#636363",high = "#a2ab58")+
#scale_fill_gradient2(low = "#355C7D",mid = "#6C5B7B",high = "#C06C84",midpoint = 1.6)+
coord_flip() +
xlab('Hallmark gene sets')+
ylab('Enrichment Score')+
labs(fill = "-log10(P)")+
theme_bw()+
theme(panel.border = element_rect(size = 1.5),
      panel.grid = element_blank(),
      axis.ticks = element_line(size = 1),
      axis.ticks.length = unit(5,'points'),
      axis.text = element_text(face = 'bold',colour = 'black'),
      axis.text.y = element_text(colour = c(rep('black',times = 4),'#BA002B','#BA002B')),
      #axis.title.x = element_text(),
      axis.title.y = element_blank()
      )

p

for (i in drivers[order(weight_shap_total_mean,decreasing = T),]$V1[1:25]){
    message(i)
}

MYL6

FN1

NQO1

GSTM3

PRDX1

LAPTM4A

TGM2

UBE2S

MDK

CD9

FOSL1

KRT8

CTSA

HIST1H2BD

ALPP

HIST1H4C

TFDP1

CSTB

MT2A

PGK1

SQSTM1

CD24

RANBP1

CD81

CKS1B

drivers_exp <- fread(file.path(read_dir,'driver_summary_shap_total_addexp.csv'))

head(drivers_exp)

drivers_exp_long<-drivers_exp %>%as.data.frame %>% 
    mutate(direction=ifelse(weight_grad_total_dir_mean > 0,'pos','neg')) %>%
    mutate(rank=rank(-drivers_exp$weight_shap_total_mean)) %>%
    mutate(top20 = ifelse(rank<=20,TRUE,FALSE)) %>%
    mutate(top10 = ifelse(rank<=10,TRUE,FALSE)) %>%
    dplyr::select(c('V1','time0_exp','time3_exp','time7_exp','time14_exp','direction','top20','top10')) %>%
    reshape2::melt(id.vars = c("V1",'direction','top20','top10'), #需保留的不参与聚合的变量列名
                  measure.vars = c('time0_exp','time3_exp','time7_exp','time14_exp'),#需要聚合的变量s1-s10
                  variable.name = c('time_point'),#聚合变量的新列名
                  value.name = 'exp')#聚合值的新列名

head(drivers_exp_long)

p<-ggplot(drivers_exp_long,aes(x=time_point,y=exp,group = V1,color = direction))+
  ggalt::geom_xspline(spline_shape = -0.5)+
  #geom_line()+
  geom_point(size=3)+
  theme_bw()+
    ggsci::scale_colour_npg()
p

Registered S3 methods overwritten by 'ggalt':
  method                  from   
  grid.draw.absoluteGrob  ggplot2
  grobHeight.absoluteGrob ggplot2
  grobWidth.absoluteGrob  ggplot2
  grobX.absoluteGrob      ggplot2
  grobY.absoluteGrob      ggplot2

Warning message:
“Using the `size` aesthetic in this geom was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` in the `default_aes` field and elsewhere instead.”

pos_drivers <- drivers_exp_long %>% filter(direction=='pos')
neg_drivers <- drivers_exp_long %>% filter(direction=='neg')

p2<-ggplot(pos_drivers%>% filter(!top20),aes(x=time_point,y=exp,group = V1,color = top20))+
  ggalt::geom_xspline(spline_shape = -0.5)+
  ggalt::geom_xspline(data = pos_drivers%>% filter(top20),spline_shape = -0.5)+
  geom_line()+
  geom_point(size=3)+
  geom_point(data = pos_drivers%>% filter(top20),size=3)+
  theme_bw()+
  scale_color_manual(values = c('TRUE'= '#D94032FF','FALSE'='#00000033'))

p2

p2<-ggplot(pos_drivers%>% filter(!top20),aes(x=time_point,y=exp,group = V1,color = top20))+
  ggbump::geom_bump(smooth = 4)+
  ggbump::geom_bump(data = pos_drivers%>% filter(top20),smooth = 4)+
  #geom_line()+
  geom_point(size=3)+
  geom_point(data = pos_drivers%>% filter(top20),size=3)+
  theme_bw()+
  scale_color_manual(values = c('TRUE'= '#D94032FF','FALSE'='#00000033'))

p2

ggsave(plot = p2,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_pos_driver_cross_time_ggbump.pdf',width =10, height =5)
ggsave(plot = p2,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_pos_driver_cross_time_ggbump.png',width =10, height =5)

#https://github.com/hrbrmstr/ggalt/issues/60
library(ggalt)
GeomXSpline <- ggplot2::ggproto("GeomXSpline", ggplot2::Geom,
                        required_aes = c("x", "y"),
                        default_aes = ggplot2::aes(colour = "black",
                                                   size = 0.5, 
                                                   linetype = 1,
                                                   alpha = 1, 
                                                   spline_shape=-1,
                                                   open=T),

                        draw_key = ggplot2::draw_key_smooth, # controls what is drawn in legend

                        draw_group = function(data, panel_params, coord) {

                          n <- nrow(data)
                          if (n <= 2) return(grid::nullGrob())

                          coords <- coord$transform(data, panel_params)

                          first_row <- coords[1, , drop = FALSE]

                          grid::xsplineGrob(
                            coords$x, coords$y,
                            shape = coords$spline_shape,
                            open = coords$open[1],
                            gp = grid::gpar(col = first_row$colour,
                                            lwd = first_row$size * .pt,
                                            alpha = first_row$alpha,
                                            lty = first_row$linetype)
                          )
                        }
)

geom_xspline <- function(mapping = NULL,
                         data = NULL,
                         stat = "identity",
                         position = "identity",
                         spline_shape = -1,
                         open = T,
                         na.rm = FALSE,
                         show.legend = NA,
                         inherit.aes = TRUE,
                         ...) {
  layer(
    geom = GeomXSpline,
    mapping = mapping,
    data = data,
    stat = stat,
    position = position,
    show.legend = show.legend,
    inherit.aes = inherit.aes,
    params = list(spline_shape = spline_shape,
                  open = open,
                  na.rm = na.rm,
                  ...)
  )
}

pos_drivers%>% filter(top20) %>% subset(time_point=='time0_exp')

#修改 R 中的 ggplot X 轴刻度标签https://www.delftstack.com/zh/howto/r/ggplot-axis-tick-labels-in-r/
#如何修改坐标轴的刻度间隔：https://blog.csdn.net/qq_42458954/article/details/112604443
p2<-ggplot(pos_drivers%>% filter(!top20),aes(x=time_point,y=exp,group = V1,color = top20))+
  geom_xspline(spline_shape = -0.5)+
  geom_xspline(data = pos_drivers%>% filter(top20),spline_shape = -0.5,size=1.5)+
  ggrepel::geom_text_repel(data=pos_drivers%>% filter(top10) %>% subset(time_point=='time0_exp'),
                  aes(label=V1),size=3, nudge_x = -0.25, segment.color = 'black')+
  geom_point(size=3)+
  geom_point(data = pos_drivers%>% filter(top20),size=4.5,shape=21,fill = 'white', stroke = 1.5)+
  xlab('Time points (Days)')+
  ylab('Normalized expression')+
  ggtitle('Time-course gene expression')+
  theme_bw()+
  scale_color_manual(values = c('TRUE'= '#259CA2BB','FALSE'='#00000033'))+
  scale_x_discrete(labels = c("time0_exp" = "0","time3_exp" = "3", "time7_exp" = "7","time14_exp" = "14"))+
  #ylim(-1.5,1.5)+
  scale_y_continuous(breaks=seq(-1.5, 1.5, 0.5),limits = c(-1.6,1.6))+
  theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5),
        axis.title.y = element_text(vjust = 6),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
       axis.text.x = element_text(vjust = -2),
        axis.text.y = element_text(hjust = -1.5),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(-10,'points'),
       axis.line = element_line(linewidth = 1),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
       panel.border = element_rect(linewidth = 1.5),
       panel.grid = element_blank(),
       #panel.grid.major.x =element_line(),
       legend.position = 'None')


p2

p3<-ggplot(data = pos_drivers%>% filter(top20),aes(x=time_point,y=exp,group = V1))+
  geom_xspline(spline_shape = -0.5,size=1.5,color= '#259CA2AA')+
  ggrepel::geom_text_repel(data=pos_drivers%>% filter(top10) %>% subset(time_point=='time0_exp'),
                  aes(label=V1),size=3, nudge_x = -0.25, segment.color = 'black',color= '#259CA2FF')+
  geom_point(data = pos_drivers%>% filter(top20),size=4.5,shape=21,fill = 'white', stroke = 1.5,color= '#259CA2FF')+
  scale_x_discrete(labels = c("time0_exp" = "0","time3_exp" = "3", "time7_exp" = "7","time14_exp" = "14"))+
  scale_y_continuous(breaks=seq(-1.5, 1.5, 0.5),limits = c(-1.6,1.6))+
  xlab('Time points (Days)')+
  ylab('Normalized expression')+
  ggtitle('Time-course gene expression')+
  theme_bw()+
  theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5),
        axis.title.y = element_text(vjust = 6),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
       axis.text.x = element_text(vjust = -2),
        axis.text.y = element_text(hjust = -1.5),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(-10,'points'),
       axis.line = element_line(linewidth = 1),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
       panel.border = element_rect(linewidth = 1.5),
       panel.grid = element_blank(),
       #panel.grid.major.x =element_line(),
       legend.position = 'None')


p3

ggsave(plot = p2,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_pos_driver_cross_time_ggalt.pdf',
       width =16/1.5, height =9/1.5)
ggsave(plot = p2,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_pos_driver_cross_time_ggalt.png',
       width =16/1.5, height =9/1.5)

ggsave(plot = p3,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_pos_driver_cross_time_ggalt_only.pdf',
       width =16/1.5, height =9/1.5)
ggsave(plot = p3,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_pos_driver_cross_time_ggalt_only.png',
       width =16/1.5, height =9/1.5)

p4<-ggplot(neg_drivers%>% filter(!top20),aes(x=time_point,y=exp,group = V1,color = top20))+
  geom_xspline(spline_shape = -0.5)+
  geom_xspline(data = neg_drivers%>% filter(top20),spline_shape = -0.5,size=1.5)+
  ggrepel::geom_text_repel(data=neg_drivers%>% filter(top10) %>% subset(time_point=='time0_exp'),
                  aes(label=V1),size=3, nudge_x = -0.25, segment.color = 'black')+
  geom_point(size=3)+
  geom_point(data = neg_drivers%>% filter(top20),size=4.5,shape=21,fill = 'white', stroke = 1.5)+
  xlab('Time points (Days)')+
  ylab('Normalized expression')+
  ggtitle('Time-course gene expression')+
  theme_bw()+
  scale_color_manual(values = c('TRUE'= '#E0A965BB','FALSE'='#00000033'))+
  scale_x_discrete(labels = c("time0_exp" = "0","time3_exp" = "3", "time7_exp" = "7","time14_exp" = "14"))+
  scale_y_continuous(breaks=seq(-1.5, 1.5, 0.5),limits = c(-1.7,1.7))+
  theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5),
        axis.title.y = element_text(vjust = 6),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
       axis.text.x = element_text(vjust = -2),
        axis.text.y = element_text(hjust = -1.5),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(-10,'points'),
       axis.line = element_line(linewidth = 1),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
       panel.border = element_rect(linewidth = 1.5),
       panel.grid = element_blank(),
       #panel.grid.major.x =element_line(),
       legend.position = 'None')


p4

p5<-ggplot(data = neg_drivers%>% filter(top20),aes(x=time_point,y=exp,group = V1))+
  geom_xspline(spline_shape = -0.5,size=1.5,color= '#E0A965AA')+
  ggrepel::geom_text_repel(data=neg_drivers%>% filter(top10) %>% subset(time_point=='time0_exp'),
                  aes(label=V1),size=3, nudge_x = -0.25, segment.color = 'black',color= '#E0A965FF')+
  geom_point(data = neg_drivers%>% filter(top20),size=4.5,shape=21,fill = 'white', stroke = 1.5,color= '#E0A965FF')+
  scale_x_discrete(labels = c("time0_exp" = "0","time3_exp" = "3", "time7_exp" = "7","time14_exp" = "14"))+
  scale_y_continuous(breaks=seq(-1.5, 1.5, 0.5),limits = c(-1.7,1.7))+
  xlab('Time points (Days)')+
  ylab('Normalized expression')+
  ggtitle('Time-course gene expression')+
  theme_bw()+
  theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5),
        axis.title.y = element_text(vjust = 6),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
       axis.text.x = element_text(vjust = -2),
        axis.text.y = element_text(hjust = -1.5),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(-10,'points'),
       axis.line = element_line(linewidth = 1),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
       panel.border = element_rect(linewidth = 1.5),
       panel.grid = element_blank(),
       #panel.grid.major.x =element_line(),
       legend.position = 'None')


p5

ggsave(plot = p4,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_neg_driver_cross_time_ggalt.pdf',
       width =16/1.5, height =9/1.5)
ggsave(plot = p4,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_neg_driver_cross_time_ggalt.png',
       width =16/1.5, height =9/1.5)

ggsave(plot = p5,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_neg_driver_cross_time_ggalt_only.pdf',
       width =16/1.5, height =9/1.5)
ggsave(plot = p5,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_neg_driver_cross_time_ggalt_only.png',
       width =16/1.5, height =9/1.5)

gene <- bitr(drivers$V1, fromType="SYMBOL", toType=c("ENTREZID"), OrgDb="org.Hs.eg.db")
gs <- drivers[order(weight_shap_total_mean,decreasing = T),]
ags <- merge(gene,gs,by.x = 'SYMBOL',by.y='V1',all=F)
gs <- ags[order(ags$weight_shap_total_mean,decreasing = T),]
gs <- gs$weight_shap_total_mean
names(gs) <- ags$ENTREZID

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(drivers$V1, fromType = "SYMBOL", toType = c("ENTREZID"), :
“6.35% of input gene IDs are fail to map...”

m_t2g <- msigdbr(species = "Homo sapiens", category = "H") %>% 
  dplyr::select(gs_name, entrez_gene)

m_t2g$gs_name <- m_t2g$gs_name %>% 
    stringr::str_replace_all(pattern = 'HALLMARK_',replacement = '') %>%
    stringr::str_replace_all(pattern = '_',replacement = ' ') %>%
    stringr::str_to_title()

kk <- enrichKEGG(gene         = names(gs),
                 #keyType      = 'uniprot',
                 organism     = 'hsa',
                 pvalueCutoff = 0.05)
#head(kk)
em <- enricher(names(gs), 
           TERM2GENE=m_t2g,
          minGSSize    = 0,
              #maxGSSize    = 500,
              pvalueCutoff = 1,
              #scoreType = "pos"
              qvalueCutoff = 1,
              #eps = eps,
              #verbose      = FALSE
              )

high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
gs_name <- em@result$Description
high_mean_ls <-c()

for (i in 1:nrow(em@result)){
    if (i==1){
        
        ls <- em@geneSets[em@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))
        
    }else{
        
    ls <- em@geneSets[em@result[i,'ID']]
    where <- which(high_df$ENTREZID %in% ls[[1]])
    tmp <- high_df[where,]
    tmp$gs <- gs_name[i]
    tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
    high_plot_df <- rbind(high_plot_df,tmp)
    high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))
        
    }
}

high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
high_plot_df <- rbind(high_plot_df,add,add)
high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序
colnames(high_plot_df) <- c('gs','Weight','mean')

#ggplot2 修改图例的一些操作 https://zhuanlan.zhihu.com/p/166529941
pRidge_H <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = 'Hallmark',fill = 'Log10 mean of weight') +
    xlab('SHAP weight')+
    ylab('Gene set')+
  scale_y_discrete(labels=function(x){stringr::str_wrap(x, width=30)})+
  scale_fill_gradientn(name = "Log10 mean \nof weight",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
plot.background = element_rect(fill = "transparent", color = NA), # bg of the plot
panel.background = element_rect(fill = "transparent"), # bg of the panel
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank(), # get rid of minor grid
legend.key.size = unit(20,'points'),
legend.text = element_text(face = 'italic',size=18),
#legend.title = element_text(face = 'bold',size=18), 
legend.title = element_text(face = 'bold',size=18),
legend.position = 'right'
       )

pRidge_H

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.487

ggsave(plot = pRidge_H,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_pRidge_H.pdf',
       width =16/1.5, height =24/1.5)
ggsave(plot = pRidge_H,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_pRidge_H.png',
       width =16/1.5, height =24/1.5)

Picking joint bandwidth of 0.487

Picking joint bandwidth of 0.487

high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
gs_name <- kk@result[1:30,]$Description
high_mean_ls <-c()

for (i in 1:nrow(kk@result[1:30,])){
    if (i==1){
        
        ls <- kk@geneSets[kk@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))
        
    }else{
        
    ls <- kk@geneSets[kk@result[i,'ID']]
    where <- which(high_df$ENTREZID %in% ls[[1]])
    tmp <- high_df[where,]
    tmp$gs <- gs_name[i]
    tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
    high_plot_df <- rbind(high_plot_df,tmp)
    high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))
        
    }
}

high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
high_plot_df <- rbind(high_plot_df,add,add)
high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序
colnames(high_plot_df) <- c('gs','Weight','mean')

pRidge_K <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = 'Hallmark',fill = 'Log10 mean of weight') +
    xlab('SHAP weight')+
    ylab('Gene set')+
  scale_y_discrete(labels=function(x){stringr::str_wrap(x, width=30)})+
  scale_fill_gradientn(name = "Log10 mean \nof weight",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
plot.background = element_rect(fill = "transparent", color = 'white'), # bg of the plot
panel.background = element_rect(fill = "transparent"), # bg of the panel
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank(), # get rid of minor grid
legend.key.size = unit(20,'points'),
legend.text = element_text(face = 'italic',size=18),
#legend.title = element_text(face = 'bold',size=18), 
legend.title = element_text(face = 'bold',size=18),
legend.position = 'right'
       )

pRidge_K

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.4

ggsave(plot = pRidge_K,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_pRidge_K.pdf',
       width =16/1.5, height =24/1.5)
ggsave(plot = pRidge_K,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_pRidge_K.png',
       width =16/1.5, height =24/1.5)

Picking joint bandwidth of 0.4

Picking joint bandwidth of 0.4

increase_control_details0 <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/main_PC9_LUNG_run10_t0_t14_cyc/increase_control_details.csv')
head(increase_control_details0)

increase_control_details7 <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/main_PC9_LUNG_run10_t7_t14_cyc/increase_control_details.csv')
head(increase_control_details7)

increase_control_details0$group = 'T0 to T14'
increase_control_details7$group = 'T7 to T14'

increase_control_details <- rbind(increase_control_details0[1:5,],increase_control_details7[1:5,])

increase_control_details

wilcox.test(score~group,data=increase_control_details,alternative = 'less',exact = F)

	Wilcoxon rank sum test with continuity correction

data:  score by group
W = 5, p-value = 0.07062
alternative hypothesis: true location shift is less than 0

#Kolmogorov-Smirnov test.
stats::ks.test(score~group,data=increase_control_details,alternative = 'greater',exact = F)

Warning message in ks.test.default(x = DATA[[1L]], y = DATA[[2L]], ...):
“p-value will be approximate in the presence of ties”

	Asymptotic two-sample Kolmogorov-Smirnov test

data:  score by group
D^+ = 0.8, p-value = 0.04076
alternative hypothesis: the CDF of T0 to T14 lies above that of T7 to T14

controlp <- ggplot(data = increase_control_details,aes(x = group,y = score,fill= group))+
stat_boxplot(geom = "errorbar",linewidth=1.5)+
geom_boxplot(outliers = F,linewidth=1.5,color='black')+
geom_jitter(width = 0.15,size=8,shape=21,stroke=1.5,alpha=0.8)+
ggsignif::geom_signif(
                      comparisons =  list(c('T0 to T14','T7 to T14')),
                      annotations= c('P-value = 0.04076'),textsize = 8,size=1.5,vjust=0) +

theme_classic()+
xlab('Time point modeling')+
ylab('Status increasing control score')+
labs(fill="Genes Type")+
theme_bw()+
scale_fill_manual(values = c('T0 to T14'= '#559073FF','T7 to T14'='#D28130FF'))+
scale_color_manual(values = c('T0 to T14'= '#559073FF','T7 to T14'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5),
    axis.title.y = element_text(vjust = 6),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(angle = 60,vjust = 0.5),
    #axis.text.y = element_text(hjust = 8),
    axis.ticks = element_line(linewidth = 1.5),
   axis.ticks.length = unit(10,'points'),
   axis.line = element_line(linewidth = 1.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   panel.border = element_blank(),
   panel.grid = element_blank(),
   #panel.grid.major.x =element_line(),
   legend.key.size = unit(20,'points'),
   legend.text = element_text(face = 'italic',size=18),
   #legend.title = element_text(face = 'bold',size=18), 
   legend.title = element_blank(),
   legend.position = 'top')
controlp

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

ggsave(plot = controlp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_controlp.pdf',
       width =16/1.5, height =16/1.5)
ggsave(plot = controlp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_controlp.png',
       width =16/1.5, height =16/1.5)

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

decrease_control_details0 <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/main_PC9_LUNG_run10_t0_t14_cyc/decrease_control_details.csv')
tail(decrease_control_details0)
decrease_control_details7 <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/main_PC9_LUNG_run10_t7_t14_cyc/decrease_control_details.csv')
tail(decrease_control_details7)

decrease_control_details0$group = 'T14 to T0'
decrease_control_details7$group = 'T14 to T7'

decrease_control_details <- rbind(decrease_control_details0[6:13,],decrease_control_details7[6:13,])

#Kolmogorov-Smirnov test.
stats::ks.test(score~group,data=decrease_control_details,alternative = 'less',exact = F)

Warning message in ks.test.default(x = DATA[[1L]], y = DATA[[2L]], ...):
“p-value will be approximate in the presence of ties”

	Asymptotic two-sample Kolmogorov-Smirnov test

data:  score by group
D^- = 0.875, p-value = 0.005248
alternative hypothesis: the CDF of T14 to T0 lies below that of T14 to T7

Dcontrolp <- ggplot(data = decrease_control_details,aes(x = group,y = score,fill= group))+
stat_boxplot(geom = "errorbar",linewidth=1.5)+
geom_boxplot(outliers = F,linewidth=1.5,color='black')+
geom_jitter(width = 0.15,size=8,shape=21,stroke=1.5,alpha=0.8)+
ggsignif::geom_signif(
                      comparisons =  list(c('T14 to T0','T14 to T7')),
                      annotations= c('P-value = 0.005248'),textsize = 8,size=1.5,vjust=0) +

theme_classic()+
xlab('Time point modeling')+
ylab('Status decreasing control score')+
labs(fill="Genes Type")+
theme_bw()+
scale_fill_manual(values = c('T14 to T0'= '#559073FF','T14 to T7'='#D28130FF'))+
scale_color_manual(values = c('T14 to T0'= '#559073FF','T14 to T7'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5),
    axis.title.y = element_text(vjust = 6),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(angle = 60,vjust = 0.5),
    #axis.text.y = element_text(hjust = 8),
    axis.ticks = element_line(linewidth = 1.5),
   axis.ticks.length = unit(10,'points'),
   axis.line = element_line(linewidth = 1.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   panel.border = element_blank(),
   panel.grid = element_blank(),
   #panel.grid.major.x =element_line(),
   legend.key.size = unit(20,'points'),
   legend.text = element_text(face = 'italic',size=18),
   #legend.title = element_text(face = 'bold',size=18), 
   legend.title = element_blank(),
   legend.position = 'top')
Dcontrolp

Warning message:
“Removed 2 rows containing non-finite outside the scale range
(`stat_boxplot()`).”
Warning message:
“Removed 2 rows containing non-finite outside the scale range
(`stat_boxplot()`).”
Warning message:
“Removed 2 rows containing non-finite outside the scale range (`stat_signif()`).”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”
Warning message:
“Removed 2 rows containing missing values or values outside the scale range
(`geom_point()`).”

ggsave(plot = Dcontrolp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_Dcontrolp.pdf',
       width =16/1.5, height =16/1.5)
ggsave(plot = Dcontrolp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_Dcontrolp.png',
       width =16/1.5, height =16/1.5)

Warning message:
“Removed 2 rows containing non-finite outside the scale range
(`stat_boxplot()`).”
Warning message:
“Removed 2 rows containing non-finite outside the scale range
(`stat_boxplot()`).”
Warning message:
“Removed 2 rows containing non-finite outside the scale range (`stat_signif()`).”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”
Warning message:
“Removed 2 rows containing missing values or values outside the scale range
(`geom_point()`).”
Warning message:
“Removed 2 rows containing non-finite outside the scale range
(`stat_boxplot()`).”
Warning message:
“Removed 2 rows containing non-finite outside the scale range
(`stat_boxplot()`).”
Warning message:
“Removed 2 rows containing non-finite outside the scale range (`stat_signif()`).”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”
Warning message:
“Removed 2 rows containing missing values or values outside the scale range
(`geom_point()`).”

increase_control_details_t7Driver<- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_adata_increase_t7Driver.csv')

increase_control_details_t7Driver$group = c(rep('T0',times = 5),rep('T14',times = 8),rep('T7',times = 5))

#Kolmogorov-Smirnov test.
tmp1 <- increase_control_details_t7Driver[c(1:5,14:18),]
stats::ks.test(score~group,data=tmp1,alternative = 'greater',exact = F)

Warning message in ks.test.default(x = DATA[[1L]], y = DATA[[2L]], ...):
“p-value will be approximate in the presence of ties”

	Asymptotic two-sample Kolmogorov-Smirnov test

data:  score by group
D^+ = 0.8, p-value = 0.04076
alternative hypothesis: the CDF of T0 lies above that of T7

controlp <- ggplot(data = increase_control_details_t7Driver[c(1:5,14:18),],aes(x = group,y = score,fill= group))+
stat_boxplot(geom = "errorbar",linewidth=1.5)+
geom_boxplot(outliers = F,linewidth=1.5,color='black')+
geom_jitter(width = 0.15,size=8,shape=21,stroke=1.5,alpha=0.8)+
ggsignif::geom_signif(
                      comparisons =  list(c('T0','T7')),
                      annotations= c('P-value = 0.04076'),textsize = 8,size=1.5,vjust=0) +

theme_classic()+
xlab('Time point modeling')+
ylab('Status increasing control score')+
labs(fill="Genes Type")+
theme_bw()+
scale_fill_manual(values = c('T0'= '#559073FF','T7'='#D28130FF'))+
scale_color_manual(values = c('T0'= '#559073FF','T7'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5),
    axis.title.y = element_text(vjust = 6),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(angle = 60,vjust = 0.5),
    #axis.text.y = element_text(hjust = 8),
    axis.ticks = element_line(linewidth = 1.5),
   axis.ticks.length = unit(10,'points'),
   axis.line = element_line(linewidth = 1.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   panel.border = element_blank(),
   panel.grid = element_blank(),
   #panel.grid.major.x =element_line(),
   legend.key.size = unit(20,'points'),
   legend.text = element_text(face = 'italic',size=18),
   #legend.title = element_text(face = 'bold',size=18), 
   legend.title = element_blank(),
   legend.position = 'top')
controlp

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

increase_control_details_t0Driver<- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_adata_increase_t0Driver.csv')

increase_control_details_t0Driver$group = c(rep('T0',times = 5),rep('T14',times = 8),rep('T7',times = 5))

#Kolmogorov-Smirnov test.
tmp1 <- increase_control_details_t0Driver[c(1:5,14:18),]
stats::ks.test(score~group,data=tmp1,alternative = 'greater',exact = F)

Warning message in ks.test.default(x = DATA[[1L]], y = DATA[[2L]], ...):
“p-value will be approximate in the presence of ties”

	Asymptotic two-sample Kolmogorov-Smirnov test

data:  score by group
D^+ = 0.8, p-value = 0.04076
alternative hypothesis: the CDF of T0 lies above that of T7

controlp <- ggplot(data = increase_control_details_t7Driver[c(1:5,14:18),],aes(x = group,y = score,fill= group))+
stat_boxplot(geom = "errorbar",linewidth=1.5)+
geom_boxplot(outliers = F,linewidth=1.5,color='black')+
geom_jitter(width = 0.15,size=8,shape=21,stroke=1.5,alpha=0.8)+
ggsignif::geom_signif(
                      comparisons =  list(c('T0','T7')),
                      annotations= c('P-value = 0.04076'),textsize = 8,size=1.5,vjust=0) +

theme_classic()+
xlab('Time point modeling')+
ylab('Status increasing control score')+
labs(fill="Genes Type")+
theme_bw()+
scale_fill_manual(values = c('T0'= '#559073FF','T7'='#D28130FF'))+
scale_color_manual(values = c('T0'= '#559073FF','T7'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5),
    axis.title.y = element_text(vjust = 6),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(angle = 60,vjust = 0.5),
    #axis.text.y = element_text(hjust = 8),
    axis.ticks = element_line(linewidth = 1.5),
   axis.ticks.length = unit(10,'points'),
   axis.line = element_line(linewidth = 1.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   panel.border = element_blank(),
   panel.grid = element_blank(),
   #panel.grid.major.x =element_line(),
   legend.key.size = unit(20,'points'),
   legend.text = element_text(face = 'italic',size=18),
   #legend.title = element_text(face = 'bold',size=18), 
   legend.title = element_blank(),
   legend.position = 'top')
controlp

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

tmp <- rbind(increase_control_details_t0Driver[c(1:5),],increase_control_details_t7Driver[c(14:18),])

#Kolmogorov-Smirnov test.
stats::ks.test(score~group,data=tmp,alternative = 'greater',exact = F)

Warning message in ks.test.default(x = DATA[[1L]], y = DATA[[2L]], ...):
“p-value will be approximate in the presence of ties”

	Asymptotic two-sample Kolmogorov-Smirnov test

data:  score by group
D^+ = 0.8, p-value = 0.04076
alternative hypothesis: the CDF of T0 lies above that of T7

controlp <- ggplot(data = tmp,aes(x = group,y = score,fill= group))+
stat_boxplot(geom = "errorbar",linewidth=1.5)+
geom_boxplot(outliers = F,linewidth=1.5,color='black')+
geom_jitter(width = 0.15,size=8,shape=21,stroke=1.5,alpha=0.8)+
ggsignif::geom_signif(
                      comparisons =  list(c('T0','T7')),
                      annotations= c('P-value = 0.04076'),textsize = 8,size=1.5,vjust=0) +

theme_classic()+
xlab('Time point modeling')+
ylab('Status increasing control score')+
labs(fill="Genes Type")+
theme_bw()+
scale_fill_manual(values = c('T0'= '#559073FF','T7'='#D28130FF'))+
scale_color_manual(values = c('T0'= '#559073FF','T7'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5),
    axis.title.y = element_text(vjust = 6),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(angle = 60,vjust = 0.5),
    #axis.text.y = element_text(hjust = 8),
    axis.ticks = element_line(linewidth = 1.5),
   axis.ticks.length = unit(10,'points'),
   axis.line = element_line(linewidth = 1.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   panel.border = element_blank(),
   panel.grid = element_blank(),
   #panel.grid.major.x =element_line(),
   legend.key.size = unit(20,'points'),
   legend.text = element_text(face = 'italic',size=18),
   #legend.title = element_text(face = 'bold',size=18), 
   legend.title = element_blank(),
   legend.position = 'top')
controlp

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

ggsave(plot = controlp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_7_controlp.pdf',
       width =16/1.5, height =16/1.5)
ggsave(plot = controlp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_7_controlp.png',
       width =16/1.5, height =16/1.5)

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

decrease_control_details_t7Driver<- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_adata_decrease_t7Driver.csv')
decrease_control_details_t0Driver<- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_adata_decrease_t0Driver.csv')

decrease_control_details_t7Driver$group = c(rep('T0',times = 5),rep('T14 T0',times = 8),rep('T7',times = 5))
decrease_control_details_t0Driver$group = c(rep('T0',times = 5),rep('T14 T7',times = 8),rep('T7',times = 5))

#Kolmogorov-Smirnov test.
tmp1 <- decrease_control_details_t7Driver[c(6:13),]
tmp2 <- decrease_control_details_t0Driver[c(6:13),]
tmp <- rbind(tmp1,tmp2)
stats::ks.test(score~group,data=tmp,alternative = 'greater',exact = F)

Warning message in ks.test.default(x = DATA[[1L]], y = DATA[[2L]], ...):
“p-value will be approximate in the presence of ties”

	Asymptotic two-sample Kolmogorov-Smirnov test

data:  score by group
D^+ = 0.625, p-value = 0.04394
alternative hypothesis: the CDF of T14 T0 lies above that of T14 T7

Dcontrolp <- ggplot(data = tmp,aes(x = group,y = score,fill= group))+
#stat_boxplot(geom = "errorbar",linewidth=1.5)+
#geom_violin(outliers = F,linewidth=1.5,color='black')+
geom_boxplot(outliers = F,linewidth=1.5,color='black')+
geom_jitter(width = 0.15,size=8,shape=21,stroke=1.5,alpha=0.8)+
ggsignif::geom_signif(
                      comparisons =  list(c('T14 T0','T14 T7')),
                      annotations= c('P-value = 0.04394'),textsize = 8,size=1.5,vjust=0) +

theme_classic()+
xlab('Time point modeling')+
ylab('Status increasing control score')+
labs(fill="Genes Type")+
theme_bw()+
scale_fill_manual(values = c('T14 T0'= '#559073FF','T14 T7'='#D28130FF'))+
scale_color_manual(values = c('T14 T0'= '#559073FF','T14 T7'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5),
    axis.title.y = element_text(vjust = 6),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(angle = 60,vjust = 0.5),
    #axis.text.y = element_text(hjust = 8),
    axis.ticks = element_line(linewidth = 1.5),
   axis.ticks.length = unit(10,'points'),
   axis.line = element_line(linewidth = 1.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   panel.border = element_blank(),
   panel.grid = element_blank(),
   #panel.grid.major.x =element_line(),
   legend.key.size = unit(20,'points'),
   legend.text = element_text(face = 'italic',size=18),
   #legend.title = element_text(face = 'bold',size=18), 
   legend.title = element_blank(),
   legend.position = 'top')
Dcontrolp

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

ggsave(plot = Dcontrolp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_7_Dcontrolp.pdf',
       width =16/1.5, height =16/1.5)
ggsave(plot = Dcontrolp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_7_Dcontrolp.png',
       width =16/1.5, height =16/1.5)

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

diff_gene_exp_meatcell4 <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/main_PC9_LUNG_run10_t0_t14_cyc/diff_gene_exp_meatcell4.csv')

head(diff_gene_exp_meatcell4)

diff_gene_exp_meatcell4 <- diff_gene_exp_meatcell4 %>%mutate(change = as.factor(ifelse(pvals < 0.05 & abs(logFC) > 1.2,
                                   ifelse(logFC > 1 ,'Up','Down'),'No change')))

dim(diff_gene_exp_meatcell4[diff_gene_exp_meatcell4$change == 'Down',])

diff_gene_exp_meatcell4[diff_gene_exp_meatcell4$change == 'Down',]

dim(diff_gene_exp_meatcell4[diff_gene_exp_meatcell4$change == 'Up',])

diff_gene_exp_meatcell4[diff_gene_exp_meatcell4$change == 'Up',]

diff_gene_exp_meatcell4[diff_gene_exp_meatcell4$Gene == 'P2RY6','logFC'] = diff_gene_exp_meatcell4[diff_gene_exp_meatcell4$Gene == 'P2RY6','logFC']+20

volcanop<- ggplot(diff_gene_exp_meatcell4 %>% filter(abs(logFC)<10),aes(logFC, -log10(pvals)))+
  geom_hline(yintercept = -log10(0.05), linetype = 5, color = "black",linewidth = 1)+
  geom_vline(xintercept = c(-1.2,1.2), linetype = 5, color = "black",linewidth = 1)+
  geom_point(aes(color = change),
             size = 4, 
             alpha = 0.75) +
  ggrepel::geom_text_repel(data =diff_gene_exp_meatcell4 %>% filter(abs(logFC)<10) %>% filter(change %in% c('Up','Down')),
                  max.overlaps = getOption("ggrepel.max.overlaps", default = 30),
                  # 这里的filter很关键，筛选你想要标记的基因
                  aes(label = Gene),
                  size = 5, box.padding = unit(2.5, "mm"),
                  color = 'black') +
  theme_bw(base_size = 12)+
  scale_color_manual(values = c('Up'='#0FB9F3','Down'='#EA5A18','No change'='#BBBBBB')) +
  theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5),
        axis.title.y = element_text(vjust = 6),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(10,'points'),
       axis.line = element_line(linewidth = 1),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
       panel.border = element_rect(linewidth = 1.5),
       panel.grid = element_blank(),
       #panel.grid.major.x =element_line(),
       legend.position = 'None')+
  xlab("Log2FC")+
  ylab("-Log10(P-value)")
volcanop

Warning message:
“ggrepel: 15 unlabeled data points (too many overlaps). Consider increasing max.overlaps”

ggsave(plot = volcanop,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_volcanop.pdf',
       width =14/1.5, height =16/1.5)
ggsave(plot = volcanop,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_volcanop.png',
       width =14/1.5, height =16/1.5)

diff_gene_exp_meatcell4[diff_gene_exp_meatcell4$change == 'Down',]$Gene %in% drivers$V1

up_0 <- diff_gene_exp_meatcell4[diff_gene_exp_meatcell4$change == 'Up',]$Gene
down_0 <- diff_gene_exp_meatcell4[diff_gene_exp_meatcell4$change == 'Down',]$Gene

diff_gene_exp_meatcell4 <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/main_PC9_LUNG_run10_t0_t14_cyc/diff_gene_exp14_meatcell4.csv')

diff_gene_exp_meatcell4 <- diff_gene_exp_meatcell4 %>%mutate(change = as.factor(ifelse(pvals < 0.05 & abs(logFC) > 1.2,
                                   ifelse(logFC > 1 ,'Up','Down'),'No change')))

volcanop<- ggplot(diff_gene_exp_meatcell4 %>% filter(abs(logFC)<10),aes(logFC, -log10(pvals)))+
  geom_hline(yintercept = -log10(0.05), linetype = 5, color = "black",linewidth = 1)+
  geom_vline(xintercept = c(-1.2,1.2), linetype = 5, color = "black",linewidth = 1)+
  geom_point(aes(color = change),
             size = 4, 
             alpha = 0.75) +
  ggrepel::geom_text_repel(data =diff_gene_exp_meatcell4 %>%
                           filter(abs(logFC)<10) %>% 
                           filter(change %in% c('Up','Down')) %>%
                           filter(-log10(pvals)>8 | abs(logFC) > 3),
                  max.overlaps = getOption("ggrepel.max.overlaps", default = 30),
                  # 这里的filter很关键，筛选你想要标记的基因
                  aes(label = Gene),
                  size = 5, box.padding = unit(2.5, "mm"),
                  color = 'black') +
  theme_bw(base_size = 12)+
  scale_color_manual(values = c('Up'='#0FB9F3','Down'='#EA5A18','No change'='#BBBBBB')) +
  theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5),
        axis.title.y = element_text(vjust = 6),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(10,'points'),
       axis.line = element_line(linewidth = 1),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
       panel.border = element_rect(linewidth = 1.5),
       panel.grid = element_blank(),
       #panel.grid.major.x =element_line(),
       legend.position = 'None')+
  xlab("Log2FC")+
  ylab("-Log10(P-value)")
volcanop

ggsave(plot = volcanop,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_volcanop_14low.pdf',
       width =14/1.5, height =16/1.5)
ggsave(plot = volcanop,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_14_volcanop_14low.png',
       width =14/1.5, height =16/1.5)

up_14 <- diff_gene_exp_meatcell4[diff_gene_exp_meatcell4$change == 'Up',]$Gene
down_14 <- diff_gene_exp_meatcell4[diff_gene_exp_meatcell4$change == 'Down',]$Gene

a <- list(up_0 = up_0,
          down_0 = down_0,
           up_14 = up_14,
           down_14 = down_14)
p1=ggvenn(a, c("up_0", "down_0","up_14",'down_14')) 
p1

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t7_t14_cyc'
read_dir <- file.path(read_dir,run_name)

drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(drivers)

drivers$rank_shap_weight = rank(-drivers$weight_shap_total_mean)
drivers$rank_grad_weight = rank(-abs(drivers$weight_grad_total_dir_mean))

drivers[drivers$is_in_Pathway,]

fread(file.path(read_dir,'all_driver_types_match_counts.csv'))

tdf <- fread(file.path(read_dir,'driver_info_0.csv')) %>% dplyr::select(c('V1','weight_shap_total'))

file_name = paste0('driver_info_',0,'.csv')
df <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
for (i in 1:9){
    file_name = paste0('driver_info_',i,'.csv')
    tdf <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
    df <- merge(df,tdf,by = 'V1',all = T,suffixes=c(i,i+1))
    
}
colnames(df) <- c('Gene',paste0('run',0:9))

plot_df <- tidyr::gather(df, key = "variable", value = "value",-Gene)

pathway_hallmark = openxlsx::read.xlsx(file.path('./resources/pathway', 'Gene_signature_list_paper_supp.xlsx'))

plot_df$pw = plot_df$Gene %in% pathway_hallmark$HALLMARK_FATTY_ACID_METABOLISM

ggplot(data = plot_df)+
geom_boxplot(aes(x=variable,y=value,fill=pw))+
theme_classic()

Warning message:
“Removed 398 rows containing non-finite outside the scale range
(`stat_boxplot()`).”

gl <- drivers[order(weight_shap_total_mean,decreasing = T),]$V1[1:10]

tmp <- plot_df[plot_df$Gene %in% gl,]

tmp$Gene <- factor(tmp$Gene,levels = rev(gl))

gl

ggplot(tmp, aes(x = value, y = Gene, fill = Gene)) +
  ggridges::geom_density_ridges() +
  ggridges::theme_ridges() + 
  theme(legend.position = "none")

Picking joint bandwidth of 0.000269

drivers$norm_shap <-  normalize(drivers$weight_shap_total_mean)
ddf <- drivers[order(drivers$weight_shap_total_mean,decreasing = T),][1:10,] %>% as.data.frame()
ddf$V1 <- factor(ddf$V1,levels = rev(ddf$V1))

bar_p <-  ggplot(ddf) +
  geom_bar(aes(x = V1, y = norm_shap,fill=norm_shap),stat = "identity",width = 0.6, alpha=1)+
    scale_fill_gradient(low = "#659999",high = "#f4791f")+
    coord_flip() +
    theme_bw()+
    ylab('Normalized SHAP weight')+
    xlab('Driver genes')+
    ggtitle("Modeling between T7 T14")+
    #scale_color_manual(values = c('In two pathway'= '#559073FF','Out of two pathway'='#D28130FF'))+
    theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5,hjust = 0.5),
        axis.title.y = element_text(vjust = 5,hjust = 0.5),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
       axis.text.x = element_text(vjust = 0.5),
       axis.text.y = element_text(colour = c(rep('black',times = 2),'#BA002B','black','#BA002B',rep('black',times = 5))),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
        panel.border = element_rect(size = 1.5),
        panel.grid = element_blank(),
        panel.grid.minor.x = element_line(linetype = 5),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(10,'points'),
       legend.position = 'none'

    )
bar_p

Warning message:
“Vectorized input to `element_text()` is not officially supported.
ℹ Results may be unexpected or may change in future versions of ggplot2.”

ggsave(plot = bar_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t7_14_bar_p.pdf',
       width =12/1.5, height =16/1.5)
ggsave(plot = bar_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t7_14_bar_p.png',
       width =12/1.5, height =16/1.5)

drivers_exp <- fread(file.path(read_dir,'driver_summary_shap_total_addexp.csv'))

drivers_exp_long<-drivers_exp %>%as.data.frame %>% 
    mutate(direction=ifelse(weight_grad_total_dir_mean > 0,'pos','neg')) %>%
    mutate(rank=rank(-drivers_exp$weight_shap_total_mean)) %>%
    mutate(top20 = ifelse(rank<=20,TRUE,FALSE)) %>%
    mutate(top10 = ifelse(rank<=10,TRUE,FALSE)) %>%
    dplyr::select(c('V1','time0_exp','time3_exp','time7_exp','time14_exp','direction','top20','top10')) %>%
    reshape2::melt(id.vars = c("V1",'direction','top20','top10'), #需保留的不参与聚合的变量列名
                  measure.vars = c('time0_exp','time3_exp','time7_exp','time14_exp'),#需要聚合的变量s1-s10
                  variable.name = c('time_point'),#聚合变量的新列名
                  value.name = 'exp')#聚合值的新列名

head(drivers_exp_long)

pos_drivers <- drivers_exp_long %>% filter(direction=='pos')
neg_drivers <- drivers_exp_long %>% filter(direction=='neg')

pos_time_p<-ggplot(pos_drivers%>% filter(!top20),aes(x=time_point,y=exp,group = V1,color = top20))+
  geom_xspline(spline_shape = -0.5)+
  geom_xspline(data = pos_drivers%>% filter(top20),spline_shape = -0.5,size=1.5)+
  ggrepel::geom_text_repel(data=pos_drivers%>% filter(top10) %>% subset(time_point=='time0_exp'),
                  aes(label=V1),size=3, nudge_x = -0.25, segment.color = 'black')+
  geom_point(size=3)+
  geom_point(data = pos_drivers%>% filter(top20),size=4.5,shape=21,fill = 'white', stroke = 1.5)+
  xlab('Time points (Days)')+
  ylab('Normalized expression')+
  ggtitle('Time-course gene expression')+
  theme_bw()+
  scale_color_manual(values = c('TRUE'= '#259CA2BB','FALSE'='#00000033'))+
  scale_x_discrete(labels = c("time0_exp" = "0","time3_exp" = "3", "time7_exp" = "7","time14_exp" = "14"))+
  #ylim(-1.5,1.5)+
  scale_y_continuous(breaks=seq(-1.5, 1.5, 0.5),limits = c(-1.6,1.6))+
  theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5),
        axis.title.y = element_text(vjust = 6),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
       axis.text.x = element_text(vjust = -2),
        axis.text.y = element_text(hjust = -1.5),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(-10,'points'),
       axis.line = element_line(linewidth = 1),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
       panel.border = element_rect(linewidth = 1.5),
       panel.grid = element_blank(),
       #panel.grid.major.x =element_line(),
       legend.position = 'None')


pos_time_p

Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_x_spline()`).”
Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_point()`).”

ggsave(plot = pos_time_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t7_14_pos_driver_cross_time_ggalt.pdf',
       width =16/1.5, height =9/1.5)
ggsave(plot = pos_time_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t7_14_pos_driver_cross_time_ggalt.png',
       width =16/1.5, height =9/1.5)

Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_x_spline()`).”
Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_point()`).”
Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_x_spline()`).”
Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_point()`).”

neg_time_p<-ggplot(neg_drivers%>% filter(!top20),aes(x=time_point,y=exp,group = V1,color = top20))+
  geom_xspline(spline_shape = -0.5)+
  geom_xspline(data = neg_drivers%>% filter(top20),spline_shape = -0.5,size=1.5)+
  ggrepel::geom_text_repel(data=neg_drivers%>% filter(top10) %>% subset(time_point=='time0_exp'),
                  aes(label=V1),size=3, nudge_x = -0.25, segment.color = 'black')+
  geom_point(size=3)+
  geom_point(data = neg_drivers%>% filter(top20),size=4.5,shape=21,fill = 'white', stroke = 1.5)+
  xlab('Time points (Days)')+
  ylab('Normalized expression')+
  ggtitle('Time-course gene expression')+
  theme_bw()+
  scale_color_manual(values = c('TRUE'= '#E0A965BB','FALSE'='#00000033'))+
  scale_x_discrete(labels = c("time0_exp" = "0","time3_exp" = "3", "time7_exp" = "7","time14_exp" = "14"))+
  scale_y_continuous(breaks=seq(-1.5, 1.5, 0.5),limits = c(-1.7,1.7))+
  theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5),
        axis.title.y = element_text(vjust = 6),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
       axis.text.x = element_text(vjust = -2),
        axis.text.y = element_text(hjust = -1.5),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(-10,'points'),
       axis.line = element_line(linewidth = 1),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
       panel.border = element_rect(linewidth = 1.5),
       panel.grid = element_blank(),
       #panel.grid.major.x =element_line(),
       legend.position = 'None')


neg_time_p

ggsave(plot = neg_time_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t7_14_neg_driver_cross_time_ggalt.pdf',
       width =16/1.5, height =9/1.5)
ggsave(plot = neg_time_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t7_14_neg_driver_cross_time_ggalt.png',
       width =16/1.5, height =9/1.5)

gene <- bitr(drivers$V1, fromType="SYMBOL", toType=c("ENTREZID"), OrgDb="org.Hs.eg.db")
gs <- drivers[order(weight_shap_total_mean,decreasing = T),]
ags <- merge(gene,gs,by.x = 'SYMBOL',by.y='V1',all=F)
gs <- ags[order(ags$weight_shap_total_mean,decreasing = T),]
gs <- gs$weight_shap_total_mean
names(gs) <- ags$ENTREZID

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(drivers$V1, fromType = "SYMBOL", toType = c("ENTREZID"), :
“1.67% of input gene IDs are fail to map...”

m_t2g <- msigdbr(species = "Homo sapiens", category = "H") %>% 
  dplyr::select(gs_name, entrez_gene)

m_t2g$gs_name <- m_t2g$gs_name %>% 
    stringr::str_replace_all(pattern = 'HALLMARK_',replacement = '') %>%
    stringr::str_replace_all(pattern = '_',replacement = ' ') %>%
    stringr::str_to_title()

kk <- enrichKEGG(gene         = names(gs),
                 #keyType      = 'uniprot',
                 organism     = 'hsa',
                 pvalueCutoff = 0.05)
#head(kk)
em <- enricher(names(gs), 
           TERM2GENE=m_t2g,
          minGSSize    = 0,
              #maxGSSize    = 500,
              pvalueCutoff = 1,
              #scoreType = "pos"
              qvalueCutoff = 1,
              #eps = eps,
              #verbose      = FALSE
              )

high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
gs_name <- em@result$Description
high_mean_ls <-c()

for (i in 1:nrow(em@result)){
    if (i==1){
        
        ls <- em@geneSets[em@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))
        
    }else{
        
    ls <- em@geneSets[em@result[i,'ID']]
    where <- which(high_df$ENTREZID %in% ls[[1]])
    tmp <- high_df[where,]
    tmp$gs <- gs_name[i]
    tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
    high_plot_df <- rbind(high_plot_df,tmp)
    high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))
        
    }
}

high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
high_plot_df <- rbind(high_plot_df,add,add)
high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序
colnames(high_plot_df) <- c('gs','Weight','mean')

pRidge <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = '   ') +
  scale_fill_gradientn(name = "Median",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.text.y = element_text(size = 10,color="black"),
        axis.text.x = element_text(size = 12,color="black"),
       panel.background = element_rect(fill = "transparent"), # bg of the panel
plot.background = element_rect(fill = "transparent", color = NA), # bg of the plot
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank() # get rid of minor grid
       )

pRidge

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.403

#ggplot2 修改图例的一些操作 https://zhuanlan.zhihu.com/p/166529941
pRidge_H <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = 'Hallmark',fill = 'Log10 mean of weight') +
    xlab('SHAP weight')+
    ylab('Gene set')+
  scale_y_discrete(labels=function(x){stringr::str_wrap(x, width=30)})+
  scale_fill_gradientn(name = "Log10 mean \nof weight",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
plot.background = element_rect(fill = "transparent", color = NA), # bg of the plot
panel.background = element_rect(fill = "transparent"), # bg of the panel
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank(), # get rid of minor grid
legend.key.size = unit(20,'points'),
legend.text = element_text(face = 'italic',size=18),
#legend.title = element_text(face = 'bold',size=18), 
legend.title = element_text(face = 'bold',size=18),
legend.position = 'right'
       )

pRidge_H

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.403

ggsave(plot = pRidge_H,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t7_14_pRidge_H.pdf',
       width =16/1.5, height =24/1.5)
ggsave(plot = pRidge_H,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t7_14_pRidge_H.png',
       width =16/1.5, height =24/1.5)

Picking joint bandwidth of 0.403

Picking joint bandwidth of 0.403

high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
gs_name <- kk@result[1:30,]$Description
high_mean_ls <-c()

for (i in 1:nrow(kk@result[1:30,])){
    if (i==1){
        
        ls <- kk@geneSets[kk@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))
        
    }else{
        
    ls <- kk@geneSets[kk@result[i,'ID']]
    where <- which(high_df$ENTREZID %in% ls[[1]])
    tmp <- high_df[where,]
    tmp$gs <- gs_name[i]
    tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
    high_plot_df <- rbind(high_plot_df,tmp)
    high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))
        
    }
}

high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
high_plot_df <- rbind(high_plot_df,add,add)
high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序
colnames(high_plot_df) <- c('gs','Weight','mean')

pRidge_K <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = 'KEGG',fill = 'Log10 mean of weight') +
    xlab('SHAP weight')+
    ylab('Gene set')+
  scale_y_discrete(labels=function(x){stringr::str_wrap(x, width=30)})+
  scale_fill_gradientn(name = "Log10 mean \nof weight",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
plot.background = element_rect(fill = "transparent", color = 'white'), # bg of the plot
panel.background = element_rect(fill = "transparent"), # bg of the panel
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank(), # get rid of minor grid
legend.key.size = unit(20,'points'),
legend.text = element_text(face = 'italic',size=18),
#legend.title = element_text(face = 'bold',size=18), 
legend.title = element_text(face = 'bold',size=18),
legend.position = 'right'
       )

pRidge_K

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.265

ggsave(plot = pRidge_K,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t7_14_pRidge_K.pdf',
       width =16/1.5, height =24/1.5)
ggsave(plot = pRidge_K,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t7_14_pRidge_K.png',
       width =16/1.5, height =24/1.5)

Picking joint bandwidth of 0.265

Picking joint bandwidth of 0.265

chord_data <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_t7_orgin_state_transition_adata_meta.csv')

chord_data <- chord_data %>% select(c('condition','metacell_label2'))

# Transform input data in a adjacency matrix
adjacencyData <- with(chord_data, table(condition, metacell_label2))

adjacencyData

             metacell_label2
condition     0 in 0 0 in 0-7 0 in 1 1 in 0 1 in 0-7 1 in 1 2 in 0 2 in 0-7
  t0 cycling     537        0      0    110        0      0    106        0
  t14 cycling      0        0    762      0        0    346      0        0
  t7 cycling       0      281      0      0      223      0      0      191
             metacell_label2
condition     2 in 1 3 in 0 3 in 0-7 3 in 1 4 in 0 4 in 0-7 4 in 1 5 in 1
  t0 cycling       0     88        0      0     37        0      0      0
  t14 cycling    237      0        0    176      0        0    159    133
  t7 cycling       0      0       87      0      0       36      0      0
             metacell_label2
condition     6 in 1 7 in 1 8 in 1
  t0 cycling       0      0      0
  t14 cycling    120     51      9
  t7 cycling       0      0      0

dim(adjacencyData)

#https://www.jianshu.com/p/1ebeaaed6f4e
library(RColorBrewer)
display.brewer.all() #显示所有调色板

grid.col <-c( brewer.pal(8, "Set2"), brewer.pal(8, "Accent"),brewer.pal(6, "Set3"))
grid.col

#https://www.jianshu.com/p/73c246b87d82
chordDiagram(
  adjacencyData,  grid.col = grid.col, 
  annotationTrack = c("grid"), 
  preAllocateTracks = list(
    track.height = max(strwidth(unlist(dimnames(adjacencyData))))
  )
)
circos.track(
  track.index = 1, panel.fun = function(x, y) {
    circos.text(
      CELL_META$xcenter, CELL_META$ylim[1], 
      CELL_META$sector.index,  facing = "clockwise", 
      niceFacing = TRUE, adj = c(0, 0.5)
    )
  }, bg.border = NA
)

pdf('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_t7_orgin_state_transition_adata_meta.pdf')
chordDiagram(
  adjacencyData,  grid.col = grid.col, 
  annotationTrack = c("grid"), 
  preAllocateTracks = list(
    track.height = max(strwidth(unlist(dimnames(adjacencyData))))
  )
)
circos.track(
  track.index = 1, panel.fun = function(x, y) {
    circos.text(
      CELL_META$xcenter, CELL_META$ylim[1], 
      CELL_META$sector.index,  facing = "clockwise", 
      niceFacing = TRUE, adj = c(0, 0.5)
    )
  }, bg.border = NA
)
dev.off()

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t14_ncyc_cyc'
read_dir <- file.path(read_dir,run_name)

drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(drivers)

drivers$rank_shap_weight = rank(-drivers$weight_shap_total_mean)
drivers$rank_grad_weight = rank(-abs(drivers$weight_grad_total_dir_mean))

drivers[drivers$is_in_Pathway,]

drivers[order(weight_shap_total_mean,decreasing = T),]

read_dir

tdf <- fread(file.path(read_dir,'driver_info_0.csv')) %>% dplyr::select(c('V1','weight_shap_total'))

file_name = paste0('driver_info_',0,'.csv')
df <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
for (i in 1:9){
    file_name = paste0('driver_info_',i,'.csv')
    tdf <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
    df <- merge(df,tdf,by = 'V1',all = T,suffixes=c(i,i+1))
    
}
colnames(df) <- c('Gene',paste0('run',0:9))

plot_df <- tidyr::gather(df, key = "variable", value = "value",-Gene)

plot_df

gl <- drivers[order(weight_shap_total_mean,decreasing = T),]$V1[1:10]

tmp <- plot_df[plot_df$Gene %in% gl,]

tmp$Gene <- factor(tmp$Gene,levels = rev(gl))

gl

ridge_p <- ggplot(tmp, aes(x = value, y = Gene, fill = Gene)) +
  ggridges::geom_density_ridges() +
  ggridges::theme_ridges() + 
  ggsci::scale_fill_npg()+
xlab('SHAP weight')+
ylab('Driver genes')+
ggtitle("Weight through model with different seeds")+
scale_color_manual(values = c('In two pathway'= '#559073FF','Out of two pathway'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   legend.position = 'none',
   panel.grid = element_blank()
      
)
ridge_p

Picking joint bandwidth of 0.000677

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

ggsave(plot = ridge_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t14_cyc_ridge_p.pdf',
       width =16/1.5, height =16/1.5)
ggsave(plot = ridge_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t14_cyc_ridge_p.png',
       width =16/1.5, height =16/1.5)

Picking joint bandwidth of 0.000677

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”
Picking joint bandwidth of 0.000677

Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

drivers_exp <- fread(file.path(read_dir,'driver_summary_shap_total_addexp.csv'))

head(drivers_exp)

drivers_exp_long<-drivers_exp %>%as.data.frame %>% 
    mutate(direction=ifelse(weight_grad_total_dir_mean > 0,'pos','neg')) %>%
    mutate(rank=rank(-drivers_exp$weight_shap_total_mean)) %>%
    mutate(top20 = ifelse(rank<=20,TRUE,FALSE)) %>%
    mutate(top10 = ifelse(rank<=10,TRUE,FALSE)) %>%
    dplyr::select(c('V1','time0_exp','time3_exp','time7_exp','time14_exp','direction','top20','top10')) %>%
    reshape2::melt(id.vars = c("V1",'direction','top20','top10'), #需保留的不参与聚合的变量列名
                  measure.vars = c('time0_exp','time3_exp','time7_exp','time14_exp'),#需要聚合的变量s1-s10
                  variable.name = c('time_point'),#聚合变量的新列名
                  value.name = 'exp')#聚合值的新列名

head(drivers_exp_long)

pos_drivers <- drivers_exp_long %>% filter(direction=='pos')
neg_drivers <- drivers_exp_long %>% filter(direction=='neg')

pos_time_p<-ggplot(pos_drivers%>% filter(!top20),aes(x=time_point,y=exp,group = V1,color = top20))+
  geom_xspline(spline_shape = -0.5)+
  geom_xspline(data = pos_drivers%>% filter(top20),spline_shape = -0.5,size=1.5)+
  ggrepel::geom_text_repel(data=pos_drivers%>% filter(top10) %>% subset(time_point=='time0_exp'),
                  aes(label=V1),size=3, nudge_x = -0.25, segment.color = 'black')+
  geom_point(size=3)+
  geom_point(data = pos_drivers%>% filter(top20),size=4.5,shape=21,fill = 'white', stroke = 1.5)+
  xlab('Time points (Days)')+
  ylab('Normalized expression')+
  ggtitle('Time-course gene expression')+
  theme_bw()+
  scale_color_manual(values = c('TRUE'= '#259CA2BB','FALSE'='#00000033'))+
  scale_x_discrete(labels = c("time0_exp" = "0","time3_exp" = "3", "time7_exp" = "7","time14_exp" = "14"))+
  #ylim(-1.5,1.5)+
  scale_y_continuous(breaks=seq(-1.5, 1.5, 0.5),limits = c(-1.6,1.6))+
  theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5),
        axis.title.y = element_text(vjust = 6),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
       axis.text.x = element_text(vjust = -2),
        axis.text.y = element_text(hjust = -1.5),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(-10,'points'),
       axis.line = element_line(linewidth = 1),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
       panel.border = element_rect(linewidth = 1.5),
       panel.grid = element_blank(),
       #panel.grid.major.x =element_line(),
       legend.position = 'None')


pos_time_p

Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_x_spline()`).”
Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_point()`).”

ggsave(plot = pos_time_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t14_cyc_pos_driver_cross_time_ggalt.pdf',
       width =16/1.5, height =9/1.5)
ggsave(plot = pos_time_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t14_cyc_pos_driver_cross_time_ggalt.png',
       width =16/1.5, height =9/1.5)

Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_x_spline()`).”
Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_point()`).”
Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_x_spline()`).”
Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_point()`).”

neg_time_p<-ggplot(neg_drivers%>% filter(!top20),aes(x=time_point,y=exp,group = V1,color = top20))+
  geom_xspline(spline_shape = -0.5)+
  geom_xspline(data = neg_drivers%>% filter(top20),spline_shape = -0.5,size=1.5)+
  ggrepel::geom_text_repel(data=neg_drivers%>% filter(top10) %>% subset(time_point=='time0_exp'),
                  aes(label=V1),size=3, nudge_x = -0.25, segment.color = 'black')+
  geom_point(size=3)+
  geom_point(data = neg_drivers%>% filter(top20),size=4.5,shape=21,fill = 'white', stroke = 1.5)+
  xlab('Time points (Days)')+
  ylab('Normalized expression')+
  ggtitle('Time-course gene expression')+
  theme_bw()+
  scale_color_manual(values = c('TRUE'= '#E0A965BB','FALSE'='#00000033'))+
  scale_x_discrete(labels = c("time0_exp" = "0","time3_exp" = "3", "time7_exp" = "7","time14_exp" = "14"))+
  scale_y_continuous(breaks=seq(-1.5, 1.5, 0.5),limits = c(-1.7,1.7))+
  theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5),
        axis.title.y = element_text(vjust = 6),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
       axis.text.x = element_text(vjust = -2),
        axis.text.y = element_text(hjust = -1.5),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(-10,'points'),
       axis.line = element_line(linewidth = 1),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
       panel.border = element_rect(linewidth = 1.5),
       panel.grid = element_blank(),
       #panel.grid.major.x =element_line(),
       legend.position = 'None')


neg_time_p

ggsave(plot = neg_time_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t14_cyc_neg_driver_cross_time_ggalt.pdf',
       width =16/1.5, height =9/1.5)
ggsave(plot = neg_time_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t14_cyc_neg_driver_cross_time_ggalt.png',
       width =16/1.5, height =9/1.5)

gene <- bitr(drivers$V1, fromType="SYMBOL", toType=c("ENTREZID"), OrgDb="org.Hs.eg.db")

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(drivers$V1, fromType = "SYMBOL", toType = c("ENTREZID"), :
“4.94% of input gene IDs are fail to map...”

kk <- enrichKEGG(gene         = gene$ENTREZID,
                 #keyType      = 'uniprot',
                 organism     = 'hsa',
                 pvalueCutoff = 0.1)
head(kk)

Reading KEGG annotation online: "https://rest.kegg.jp/link/hsa/pathway"...

Reading KEGG annotation online: "https://rest.kegg.jp/list/pathway/hsa"...

gene <- bitr(drivers$V1, fromType="SYMBOL", toType=c("ENTREZID"), OrgDb="org.Hs.eg.db")
gs <- drivers[order(weight_shap_total_mean,decreasing = T),]
ags <- merge(gene,gs,by.x = 'SYMBOL',by.y='V1',all=F)
gs <- ags[order(ags$weight_shap_total_mean,decreasing = T),]
gs <- gs$weight_shap_total_mean
names(gs) <- ags$ENTREZID

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(drivers$V1, fromType = "SYMBOL", toType = c("ENTREZID"), :
“4.94% of input gene IDs are fail to map...”

m_t2g <- msigdbr(species = "Homo sapiens", category = "H") %>% 
  dplyr::select(gs_name, entrez_gene)

m_t2g$gs_name <- m_t2g$gs_name %>% 
    stringr::str_replace_all(pattern = 'HALLMARK_',replacement = '') %>%
    stringr::str_replace_all(pattern = '_',replacement = ' ') %>%
    stringr::str_to_title()

kk <- enrichKEGG(gene         = names(gs),
                 #keyType      = 'uniprot',
                 organism     = 'hsa',
                 pvalueCutoff = 0.05)
#head(kk)
em <- enricher(names(gs), 
           TERM2GENE=m_t2g,
          minGSSize    = 0,
              #maxGSSize    = 500,
              pvalueCutoff = 1,
              #scoreType = "pos"
              qvalueCutoff = 1,
              #eps = eps,
              #verbose      = FALSE
              )

high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
gs_name <- em@result$Description
high_mean_ls <-c()

for (i in 1:nrow(em@result)){
    if (i==1){
        
        ls <- em@geneSets[em@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))
        
    }else{
        
    ls <- em@geneSets[em@result[i,'ID']]
    where <- which(high_df$ENTREZID %in% ls[[1]])
    tmp <- high_df[where,]
    tmp$gs <- gs_name[i]
    tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
    high_plot_df <- rbind(high_plot_df,tmp)
    high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))
        
    }
}

high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
high_plot_df <- rbind(high_plot_df,add,add)
high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序
colnames(high_plot_df) <- c('gs','Weight','mean')

#ggplot2 修改图例的一些操作 https://zhuanlan.zhihu.com/p/166529941
pRidge_H <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = 'Hallmark',fill = 'Log10 mean of weight') +
    xlab('SHAP weight')+
    ylab('Gene set')+
  scale_y_discrete(labels=function(x){stringr::str_wrap(x, width=30)})+
  scale_fill_gradientn(name = "Log10 mean \nof weight",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
plot.background = element_rect(fill = "transparent", color = NA), # bg of the plot
panel.background = element_rect(fill = "transparent"), # bg of the panel
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank(), # get rid of minor grid
legend.key.size = unit(20,'points'),
legend.text = element_text(face = 'italic',size=18),
#legend.title = element_text(face = 'bold',size=18), 
legend.title = element_text(face = 'bold',size=18),
legend.position = 'right'
       )

pRidge_H

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.322

ggsave(plot = pRidge_H,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t14_cyc_pRidge_H.pdf',
       width =16/1.5, height =24/1.5)
ggsave(plot = pRidge_H,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t14_cyc_pRidge_H.png',
       width =16/1.5, height =24/1.5)

Picking joint bandwidth of 0.322

Picking joint bandwidth of 0.322

high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
gs_name <- kk@result[1:30,]$Description
high_mean_ls <-c()

for (i in 1:nrow(kk@result[1:30,])){
    if (i==1){
        
        ls <- kk@geneSets[kk@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))
        
    }else{
        
    ls <- kk@geneSets[kk@result[i,'ID']]
    where <- which(high_df$ENTREZID %in% ls[[1]])
    tmp <- high_df[where,]
    tmp$gs <- gs_name[i]
    tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
    high_plot_df <- rbind(high_plot_df,tmp)
    high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))
        
    }
}

high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
high_plot_df <- rbind(high_plot_df,add,add)
high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序
colnames(high_plot_df) <- c('gs','Weight','mean')

pRidge_K <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = 'KEGG',fill = 'Log10 mean of weight') +
    xlab('SHAP weight')+
    ylab('Gene set')+
  scale_y_discrete(labels=function(x){stringr::str_wrap(x, width=30)})+
  scale_fill_gradientn(name = "Log10 mean \nof weight",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
plot.background = element_rect(fill = "transparent", color = 'white'), # bg of the plot
panel.background = element_rect(fill = "transparent"), # bg of the panel
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank(), # get rid of minor grid
legend.key.size = unit(20,'points'),
legend.text = element_text(face = 'italic',size=18),
#legend.title = element_text(face = 'bold',size=18), 
legend.title = element_text(face = 'bold',size=18),
legend.position = 'right'
       )

pRidge_K

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.276

ggsave(plot = pRidge_K,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t14_cyc_pRidge_K.pdf',
       width =16/1.5, height =24/1.5)
ggsave(plot = pRidge_K,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t14_cyc_pRidge_K.png',
       width =16/1.5, height =24/1.5)

Picking joint bandwidth of 0.276

Picking joint bandwidth of 0.276

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t0_ncyc_cyc'
read_dir <- file.path(read_dir,run_name)

drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(drivers)

drivers$rank_shap_weight = rank(-drivers$weight_shap_total_mean)
drivers$rank_grad_weight = rank(-abs(drivers$weight_grad_total_dir_mean))

drivers[drivers$is_in_Pathway,]

tdf <- fread(file.path(read_dir,'driver_info_0.csv')) %>% dplyr::select(c('V1','weight_shap_total'))

file_name = paste0('driver_info_',0,'.csv')
df <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
for (i in 1:9){
    file_name = paste0('driver_info_',i,'.csv')
    tdf <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
    df <- merge(df,tdf,by = 'V1',all = T,suffixes=c(i,i+1))
    
}
colnames(df) <- c('Gene',paste0('run',0:9))

plot_df <- tidyr::gather(df, key = "variable", value = "value",-Gene)

plot_df

gl <- drivers[order(weight_shap_total_mean,decreasing = T),]$V1[1:10]

tmp <- plot_df[plot_df$Gene %in% gl,]

tmp$Gene <- factor(tmp$Gene,levels = rev(gl))

gl

ridge_p <- ggplot(tmp, aes(x = value, y = Gene, fill = Gene)) +
  ggridges::geom_density_ridges() +
  ggridges::theme_ridges() + 
  ggsci::scale_fill_npg()+
xlab('SHAP weight')+
ylab('Driver genes')+
ggtitle("Weight through model with different seeds")+
scale_color_manual(values = c('In two pathway'= '#559073FF','Out of two pathway'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   legend.position = 'none',
   panel.grid = element_blank()
      
)
ridge_p

Picking joint bandwidth of 0.000171

Warning message:
“Removed 1 row containing non-finite outside the scale range
(`stat_density_ridges()`).”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

ggsave(plot = ridge_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_cyc_ridge_p.pdf',
       width =16/1.5, height =16/1.5)
ggsave(plot = ridge_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_cyc_ridge_p.png',
       width =16/1.5, height =16/1.5)

Picking joint bandwidth of 0.000171

Warning message:
“Removed 1 row containing non-finite outside the scale range
(`stat_density_ridges()`).”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”
Picking joint bandwidth of 0.000171

Warning message:
“Removed 1 row containing non-finite outside the scale range
(`stat_density_ridges()`).”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

drivers_exp <- fread(file.path(read_dir,'driver_summary_shap_total_addexp.csv'))

head(drivers_exp)

drivers_exp_long<-drivers_exp %>%as.data.frame %>% 
    mutate(direction=ifelse(weight_grad_total_dir_mean > 0,'pos','neg')) %>%
    mutate(rank=rank(-drivers_exp$weight_shap_total_mean)) %>%
    mutate(top20 = ifelse(rank<=20,TRUE,FALSE)) %>%
    mutate(top10 = ifelse(rank<=10,TRUE,FALSE)) %>%
    dplyr::select(c('V1','time0_exp','time3_exp','time7_exp','time14_exp','direction','top20','top10')) %>%
    reshape2::melt(id.vars = c("V1",'direction','top20','top10'), #需保留的不参与聚合的变量列名
                  measure.vars = c('time0_exp','time3_exp','time7_exp','time14_exp'),#需要聚合的变量s1-s10
                  variable.name = c('time_point'),#聚合变量的新列名
                  value.name = 'exp')#聚合值的新列名

head(drivers_exp_long)

pos_drivers <- drivers_exp_long %>% filter(direction=='pos')
neg_drivers <- drivers_exp_long %>% filter(direction=='neg')

pos_time_p<-ggplot(pos_drivers%>% filter(!top20),aes(x=time_point,y=exp,group = V1,color = top20))+
  geom_xspline(spline_shape = -0.5)+
  geom_xspline(data = pos_drivers%>% filter(top20),spline_shape = -0.5,size=1.5)+
  ggrepel::geom_text_repel(data=pos_drivers%>% filter(top10) %>% subset(time_point=='time0_exp'),
                  aes(label=V1),size=3, nudge_x = -0.25, segment.color = 'black')+
  geom_point(size=3)+
  geom_point(data = pos_drivers%>% filter(top20),size=4.5,shape=21,fill = 'white', stroke = 1.5)+
  xlab('Time points (Days)')+
  ylab('Normalized expression')+
  ggtitle('Time-course gene expression')+
  theme_bw()+
  scale_color_manual(values = c('TRUE'= '#259CA2BB','FALSE'='#00000033'))+
  scale_x_discrete(labels = c("time0_exp" = "0","time3_exp" = "3", "time7_exp" = "7","time14_exp" = "14"))+
  #ylim(-1.5,1.5)+
  scale_y_continuous(breaks=seq(-1.5, 1.5, 0.5),limits = c(-1.6,1.6))+
  theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5),
        axis.title.y = element_text(vjust = 6),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
       axis.text.x = element_text(vjust = -2),
        axis.text.y = element_text(hjust = -1.5),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(-10,'points'),
       axis.line = element_line(linewidth = 1),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
       panel.border = element_rect(linewidth = 1.5),
       panel.grid = element_blank(),
       #panel.grid.major.x =element_line(),
       legend.position = 'None')


pos_time_p

ggsave(plot = pos_time_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_cyc_pos_driver_cross_time_ggalt.pdf',
       width =16/1.5, height =9/1.5)
ggsave(plot = pos_time_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_cyc_pos_driver_cross_time_ggalt.png',
       width =16/1.5, height =9/1.5)

Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_x_spline()`).”
Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_point()`).”
Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_x_spline()`).”
Warning message:
“Removed 1 row containing missing values or values outside the scale range
(`geom_point()`).”

neg_time_p<-ggplot(neg_drivers%>% filter(!top20),aes(x=time_point,y=exp,group = V1,color = top20))+
  geom_xspline(spline_shape = -0.5)+
  geom_xspline(data = neg_drivers%>% filter(top20),spline_shape = -0.5,size=1.5)+
  ggrepel::geom_text_repel(data=neg_drivers%>% filter(top10) %>% subset(time_point=='time0_exp'),
                  aes(label=V1),size=3, nudge_x = -0.25, segment.color = 'black')+
  geom_point(size=3)+
  geom_point(data = neg_drivers%>% filter(top20),size=4.5,shape=21,fill = 'white', stroke = 1.5)+
  xlab('Time points (Days)')+
  ylab('Normalized expression')+
  ggtitle('Time-course gene expression')+
  theme_bw()+
  scale_color_manual(values = c('TRUE'= '#E0A965BB','FALSE'='#00000033'))+
  scale_x_discrete(labels = c("time0_exp" = "0","time3_exp" = "3", "time7_exp" = "7","time14_exp" = "14"))+
  scale_y_continuous(breaks=seq(-1.5, 1.5, 0.5),limits = c(-1.7,1.7))+
  theme(axis.title = element_text(face = 'bold',size=20),
        axis.title.x = element_text(vjust = -5),
        axis.title.y = element_text(vjust = 6),
       axis.text = element_text(face = 'italic',size=18,colour = 'black'),
       axis.text.x = element_text(vjust = -2),
        axis.text.y = element_text(hjust = -1.5),
        axis.ticks = element_line(linewidth = 1.5),
       axis.ticks.length = unit(-10,'points'),
       axis.line = element_line(linewidth = 1),
       plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
       plot.margin = margin(50,50,50,50),
       panel.border = element_rect(linewidth = 1.5),
       panel.grid = element_blank(),
       #panel.grid.major.x =element_line(),
       legend.position = 'None')


neg_time_p

ggsave(plot = neg_time_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_cyc_neg_driver_cross_time_ggalt.pdf',
       width =16/1.5, height =9/1.5)
ggsave(plot = neg_time_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_cyc_neg_driver_cross_time_ggalt.png',
       width =16/1.5, height =9/1.5)

gene <- bitr(drivers$V1, fromType="SYMBOL", toType=c("ENTREZID"), OrgDb="org.Hs.eg.db")

'select()' returned 1:1 mapping between keys and columns

kk <- enrichKEGG(gene         = gene$ENTREZID,
                 #keyType      = 'uniprot',
                 organism     = 'hsa',
                 pvalueCutoff = 0.1)
head(kk)

gs <- drivers[order(weight_shap_total_mean,decreasing = T),]
ags <- merge(gene,gs,by.x = 'SYMBOL',by.y='V1',all=F)
gs <- ags[order(ags$weight_shap_total_mean,decreasing = T),]
gs <- gs$weight_shap_total_mean
names(gs) <- ags$ENTREZID

em <- enricher(names(gs), 
           TERM2GENE=m_t2g,
          minGSSize    = 0,
              #maxGSSize    = 500,
              pvalueCutoff = 1,
              #scoreType = "pos"
              qvalueCutoff = 1,
              #eps = eps,
              #verbose      = FALSE
              )
head(em)

high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
gs_name <- em@result$Description
high_mean_ls <-c()

for (i in 1:nrow(em@result)){
    if (i==1){
        
        ls <- em@geneSets[em@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))
        
    }else{
        
    ls <- em@geneSets[em@result[i,'ID']]
    where <- which(high_df$ENTREZID %in% ls[[1]])
    tmp <- high_df[where,]
    tmp$gs <- gs_name[i]
    tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
    high_plot_df <- rbind(high_plot_df,tmp)
    high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))
        
    }
}

high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

length(table(high_plot_df$gs))
table(high_plot_df$gs)

                     Adipogenesis           Cholesterol Homeostasis 
                                1                                 2 
                      Coagulation                        Complement 
                                2                                 1 
                       Dna Repair                       E2f Targets 
                                1                                 1 
Epithelial Mesenchymal Transition           Estrogen Response Early 
                                2                                 4 
           Estrogen Response Late                    G2m Checkpoint 
                                3                                 2 
                       Glycolysis                   Heme Metabolism 
                                1                                 1 
                          Hypoxia               Il2 Stat5 Signaling 
                                2                                 3 
          Il6 Jak Stat3 Signaling                 Kras Signaling Dn 
                                1                                 1 
                Kras Signaling Up                   Mitotic Spindle 
                                2                                 1 
                 Mtorc1 Signaling                    Myc Targets V1 
                                5                                 3 
                       Myogenesis                       P53 Pathway 
                                1                                 2 
          Pi3k Akt Mtor Signaling                Tgf Beta Signaling 
                                1                                 2 
          Tnfa Signaling Via Nfkb                    Uv Response Up 
                                5                                 1 
            Xenobiotic Metabolism 
                                1

add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
add

high_plot_df <- rbind(high_plot_df,add,add)
length(table(high_plot_df$gs))
table(high_plot_df$gs)

                     HALLMARK_ADIPOGENESIS 
                                         3 
          HALLMARK_CHOLESTEROL_HOMEOSTASIS 
                                         6 
                      HALLMARK_COAGULATION 
                                         6 
                       HALLMARK_COMPLEMENT 
                                         3 
                       HALLMARK_DNA_REPAIR 
                                         3 
                      HALLMARK_E2F_TARGETS 
                                         3 
HALLMARK_EPITHELIAL_MESENCHYMAL_TRANSITION 
                                         6 
          HALLMARK_ESTROGEN_RESPONSE_EARLY 
                                         4 
           HALLMARK_ESTROGEN_RESPONSE_LATE 
                                         3 
                   HALLMARK_G2M_CHECKPOINT 
                                         6 
                       HALLMARK_GLYCOLYSIS 
                                         3 
                  HALLMARK_HEME_METABOLISM 
                                         3 
                          HALLMARK_HYPOXIA 
                                         6 
              HALLMARK_IL2_STAT5_SIGNALING 
                                         3 
          HALLMARK_IL6_JAK_STAT3_SIGNALING 
                                         3 
                HALLMARK_KRAS_SIGNALING_DN 
                                         3 
                HALLMARK_KRAS_SIGNALING_UP 
                                         6 
                  HALLMARK_MITOTIC_SPINDLE 
                                         3 
                 HALLMARK_MTORC1_SIGNALING 
                                         5 
                   HALLMARK_MYC_TARGETS_V1 
                                         3 
                       HALLMARK_MYOGENESIS 
                                         3 
                      HALLMARK_P53_PATHWAY 
                                         6 
          HALLMARK_PI3K_AKT_MTOR_SIGNALING 
                                         3 
               HALLMARK_TGF_BETA_SIGNALING 
                                         6 
          HALLMARK_TNFA_SIGNALING_VIA_NFKB 
                                         5 
                   HALLMARK_UV_RESPONSE_UP 
                                         3 
            HALLMARK_XENOBIOTIC_METABOLISM 
                                         3

high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
head(high_plot_df)

high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序

colnames(high_plot_df) <- c('gs','Weight','mean')

pRidge <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = '   ') +
  scale_fill_gradientn(name = "Median",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.text.y = element_text(size = 10,color="black"),
        axis.text.x = element_text(size = 12,color="black"),
       panel.background = element_rect(fill = "transparent"), # bg of the panel
plot.background = element_rect(fill = "transparent", color = NA), # bg of the plot
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank() # get rid of minor grid
       )

pRidge

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.539

png('weight_pRidge_all_meancolor_t0_c_nc.png',height = 500*5,width = 600*5,res=400)
    pRidge
dev.off()

Picking joint bandwidth of 0.539

gene <- bitr(drivers$V1, fromType="SYMBOL", toType=c("ENTREZID"), OrgDb="org.Hs.eg.db")
gs <- drivers[order(weight_shap_total_mean,decreasing = T),]
ags <- merge(gene,gs,by.x = 'SYMBOL',by.y='V1',all=F)
gs <- ags[order(ags$weight_shap_total_mean,decreasing = T),]
gs <- gs$weight_shap_total_mean
names(gs) <- ags$ENTREZID

'select()' returned 1:1 mapping between keys and columns

m_t2g <- msigdbr(species = "Homo sapiens", category = "H") %>% 
  dplyr::select(gs_name, entrez_gene)

m_t2g$gs_name <- m_t2g$gs_name %>% 
    stringr::str_replace_all(pattern = 'HALLMARK_',replacement = '') %>%
    stringr::str_replace_all(pattern = '_',replacement = ' ') %>%
    stringr::str_to_title()

kk <- enrichKEGG(gene         = names(gs),
                 #keyType      = 'uniprot',
                 organism     = 'hsa',
                 pvalueCutoff = 0.05)
#head(kk)
em <- enricher(names(gs), 
           TERM2GENE=m_t2g,
          minGSSize    = 0,
              #maxGSSize    = 500,
              pvalueCutoff = 1,
              #scoreType = "pos"
              qvalueCutoff = 1,
              #eps = eps,
              #verbose      = FALSE
              )

high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
gs_name <- em@result$Description
high_mean_ls <-c()

for (i in 1:nrow(em@result)){
    if (i==1){
        
        ls <- em@geneSets[em@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))
        
    }else{
        
    ls <- em@geneSets[em@result[i,'ID']]
    where <- which(high_df$ENTREZID %in% ls[[1]])
    tmp <- high_df[where,]
    tmp$gs <- gs_name[i]
    tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
    high_plot_df <- rbind(high_plot_df,tmp)
    high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))
        
    }
}

high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
high_plot_df <- rbind(high_plot_df,add,add)
high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序
colnames(high_plot_df) <- c('gs','Weight','mean')

#ggplot2 修改图例的一些操作 https://zhuanlan.zhihu.com/p/166529941
pRidge_H <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = 'Hallmark',fill = 'Log10 mean of weight') +
    xlab('SHAP weight')+
    ylab('Gene set')+
  scale_y_discrete(labels=function(x){stringr::str_wrap(x, width=30)})+
  scale_fill_gradientn(name = "Log10 mean \nof weight",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
plot.background = element_rect(fill = "transparent", color = NA), # bg of the plot
panel.background = element_rect(fill = "transparent"), # bg of the panel
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank(), # get rid of minor grid
legend.key.size = unit(20,'points'),
legend.text = element_text(face = 'italic',size=18),
#legend.title = element_text(face = 'bold',size=18), 
legend.title = element_text(face = 'bold',size=18),
legend.position = 'right'
       )

pRidge_H

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.539

ggsave(plot = pRidge_H,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_cyc_pRidge_H.pdf',
       width =16/1.5, height =24/1.5)
ggsave(plot = pRidge_H,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_cyc_pRidge_H.png',
       width =16/1.5, height =24/1.5)

Picking joint bandwidth of 0.539

Picking joint bandwidth of 0.539

high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
gs_name <- kk@result[1:30,]$Description
high_mean_ls <-c()

for (i in 1:nrow(kk@result[1:30,])){
    if (i==1){
        
        ls <- kk@geneSets[kk@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))
        
    }else{
        
    ls <- kk@geneSets[kk@result[i,'ID']]
    where <- which(high_df$ENTREZID %in% ls[[1]])
    tmp <- high_df[where,]
    tmp$gs <- gs_name[i]
    tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
    high_plot_df <- rbind(high_plot_df,tmp)
    high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))
        
    }
}

high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
high_plot_df <- rbind(high_plot_df,add,add)
high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序
colnames(high_plot_df) <- c('gs','Weight','mean')

pRidge_K <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = 'KEGG',fill = 'Log10 mean of weight') +
    xlab('SHAP weight')+
    ylab('Gene set')+
  scale_y_discrete(labels=function(x){stringr::str_wrap(x, width=30)})+
  scale_fill_gradientn(name = "Log10 mean \nof weight",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
plot.background = element_rect(fill = "transparent", color = 'white'), # bg of the plot
panel.background = element_rect(fill = "transparent"), # bg of the panel
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank(), # get rid of minor grid
legend.key.size = unit(20,'points'),
legend.text = element_text(face = 'italic',size=18),
#legend.title = element_text(face = 'bold',size=18), 
legend.title = element_text(face = 'bold',size=18),
legend.position = 'right'
       )

pRidge_K

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.52

ggsave(plot = pRidge_K,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_cyc_pRidge_K.pdf',
       width =16/1.5, height =24/1.5)
ggsave(plot = pRidge_K,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/t0_cyc_pRidge_K.png',
       width =16/1.5, height =24/1.5)

Picking joint bandwidth of 0.52

Picking joint bandwidth of 0.52

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t0_t14_cyc'
read_dir <- file.path(read_dir,run_name)

drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))

drivers$rank_shap_weight = rank(-drivers$weight_shap_total_mean)
drivers$rank_grad_weight = rank(-abs(drivers$weight_grad_total_dir_mean))

pathway_hallmark = openxlsx::read.xlsx(file.path('./resources/pathway', 'Gene_signature_list_paper_supp.xlsx'))

plot_df$pw = 'Other'
plot_df[plot_df$Gene %in% pathway_hallmark$HALLMARK_REACTIVE_OXYGEN_SPECIES_PATHWAY,]$pw <- 'ROS'
plot_df[plot_df$Gene %in% pathway_hallmark$HALLMARK_FATTY_ACID_METABOLISM,]$pw <- 'FAM'
plot_df$pw <- factor(plot_df$pw ,levels = c('Other','ROS','FAM'))

ggplot(data = plot_df)+
geom_boxplot(aes(x=variable,y=value,fill=pw))+
theme_classic()

Warning message:
“Removed 408 rows containing non-finite outside the scale range
(`stat_boxplot()`).”

normalize <- function(v) {
  (v - min(v)) / (max(v) - min(v))
}

drivers$norm_shap <-  normalize(drivers$weight_shap_total_mean)
ddf <- drivers[order(drivers$weight_shap_total_mean,decreasing = T),][1:10,] %>% as.data.frame()
ddf$V1 <- factor(ddf$V1,levels = ddf$V1)

ggplot(ddf) +
  geom_bar(aes(x = V1, y = norm_shap),stat = "identity",fill=rgb(0.1,0.4,0.5,0.7))+
    theme_classic()

tdf <- fread(file.path(read_dir,'driver_info_0.csv')) %>% dplyr::select(c('V1','weight_shap_total'))

file_name = paste0('driver_info_',0,'.csv')
df <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
for (i in 1:9){
    file_name = paste0('driver_info_',i,'.csv')
    tdf <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
    df <- merge(df,tdf,by = 'V1',all = T,suffixes=c(i,i+1))
    
}
colnames(df) <- c('Gene',paste0('run',0:9))

plot_df <- tidyr::gather(df, key = "variable", value = "value",-Gene)
plot_df <- na.omit(plot_df)
plot_df$value <- normalize(plot_df$value)

gl <- ddf$V1
tmp <- plot_df[plot_df$Gene %in% gl,]

tmp$Gene <- factor(tmp$Gene,levels = rev(gl))

ggplot(tmp, aes(x = value, y = Gene, fill = Gene)) +
  ggridges::geom_density_ridges() +
  ggridges::theme_ridges() + 
  theme(legend.position = "none")

Picking joint bandwidth of 0.0311

gene <- bitr(drivers$V1, fromType="SYMBOL", toType=c("ENTREZID"), OrgDb="org.Hs.eg.db")
gs <- drivers[order(weight_shap_total_mean,decreasing = T),]
ags <- merge(gene,gs,by.x = 'SYMBOL',by.y='V1',all=F)
gs <- ags[order(ags$weight_shap_total_mean,decreasing = T),]
gs <- gs$weight_shap_total_mean
names(gs) <- ags$ENTREZID

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(drivers$V1, fromType = "SYMBOL", toType = c("ENTREZID"), :
“6.35% of input gene IDs are fail to map...”

m_t2g <- msigdbr(species = "Homo sapiens", category = "H") %>% 
  dplyr::select(gs_name, entrez_gene)

kk <- enrichKEGG(gene         = names(gs),
                 #keyType      = 'uniprot',
                 organism     = 'hsa',
                 pvalueCutoff = 0.05)
#head(kk)
em <- enricher(names(gs), 
           TERM2GENE=m_t2g,
          minGSSize    = 0,
              #maxGSSize    = 500,
              pvalueCutoff = 1,
              #scoreType = "pos"
              qvalueCutoff = 1,
              #eps = eps,
              #verbose      = FALSE
              )

high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
gs_name <- em@result$Description
high_mean_ls <-c()

for (i in 1:nrow(em@result)){
    if (i==1){
        
        ls <- em@geneSets[em@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))
        
    }else{
        
    ls <- em@geneSets[em@result[i,'ID']]
    where <- which(high_df$ENTREZID %in% ls[[1]])
    tmp <- high_df[where,]
    tmp$gs <- gs_name[i]
    tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
    high_plot_df <- rbind(high_plot_df,tmp)
    high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))
        
    }
}

high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
high_plot_df <- rbind(high_plot_df,add,add)
high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序
colnames(high_plot_df) <- c('gs','Weight','mean')

pRidge <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = '   ') +
  scale_fill_gradientn(name = "Median",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.text.y = element_text(size = 10,color="black"),
        axis.text.x = element_text(size = 12,color="black"),
       panel.background = element_rect(fill = "transparent"), # bg of the panel
plot.background = element_rect(fill = "transparent", color = NA), # bg of the plot
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank() # get rid of minor grid
       )

pRidge

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.487

high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
gs_name <- kk@result[1:30,]$Description
high_mean_ls <-c()

for (i in 1:nrow(kk@result[1:30,])){
    if (i==1){
        
        ls <- kk@geneSets[kk@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))
        
    }else{
        
    ls <- kk@geneSets[kk@result[i,'ID']]
    where <- which(high_df$ENTREZID %in% ls[[1]])
    tmp <- high_df[where,]
    tmp$gs <- gs_name[i]
    tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
    high_plot_df <- rbind(high_plot_df,tmp)
    high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))
        
    }
}

high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
high_plot_df <- rbind(high_plot_df,add,add)
high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序
colnames(high_plot_df) <- c('gs','Weight','mean')

pRidge <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = '   ') +
  scale_fill_gradientn(name = "Median",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.text.y = element_text(size = 10,color="black"),
        axis.text.x = element_text(size = 12,color="black"),
       panel.background = element_rect(fill = "transparent"), # bg of the panel
plot.background = element_rect(fill = "transparent", color = NA), # bg of the plot
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank() # get rid of minor grid
       )

pRidge

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.4

pdf('weight_pRidge_all_meancolor_t0_c_nc.pdf',height = 500*5,width = 600*5)
    pRidge
dev.off()

tdf <- fread(file.path(read_dir,'driver_info_0.csv')) %>% select(c('V1','weight_shap_total'))

file_name = paste0('driver_info_',0,'.csv')
df <- fread(file.path(read_dir,file_name)) %>% select(c('V1','weight_shap_total'))
for (i in 1:9){
    file_name = paste0('driver_info_',i,'.csv')
    tdf <- fread(file.path(read_dir,file_name)) %>% select(c('V1','weight_shap_total'))
    df <- merge(df,tdf,by = 'V1',all = T,suffixes=c(i,i+1))
    
}
colnames(df) <- c('Gene',paste0('run',0:9))

plot_df <- tidyr::gather(df, key = "variable", value = "value",-Gene)

normalize <- function(v) {
  (v - min(v)) / (max(v) - min(v))
}
draw_ridge <- function(em,ags,name,cut=30){
    
    
    high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
    result <- em@result
    if (nrow(result) >=30){
        result <- result[1:30,]
    }
    gs_name <- result$Description
    high_mean_ls <-c()

    for (i in 1:nrow(result)){
        if (i==1){

            ls <- em@geneSets[em@result[i,'ID']]
            where <- which(high_df$ENTREZID %in% ls[[1]])
            tmp <- high_df[where,]
            tmp$gs <- gs_name[i]
            high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
            high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))

        }else{

        ls <- em@geneSets[em@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_plot_df <- rbind(high_plot_df,tmp)
        high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))

        }
    }

    high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

    add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
    high_plot_df <- rbind(high_plot_df,add,add)
    high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
    high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
    high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序
    colnames(high_plot_df) <- c('gs','Weight','mean')
    
    pRidge <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
          ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
          labs(title = '   ') +
          scale_fill_gradientn(name = "Median",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
          theme(axis.text.y = element_text(size = 10,color="black"),
                axis.text.x = element_text(size = 12,color="black"),
               panel.background = element_rect(fill = "transparent"), # bg of the panel
        plot.background = element_rect(fill = "transparent", color = NA), # bg of the plot
        panel.grid.major = element_blank(), # get rid of major grid
        panel.grid.minor = element_blank() # get rid of minor grid
               )

    #pdf(paste0(name,'_weight_pRidge_all_meancolor.pdf'),height = 5,width = 6)
    #pRidge
    #dev.off()
    ggsave(pRidge,filename = paste0(name,'_weight_pRidge_all_meancolor.pdf'),height = 250/30.48,width = 300/30.48)
}
pipe_n <- function(run_name){
    read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
    #run_name <- 'main_PC9_LUNG_run10_t0_t14_cyc'
    read_dir <- file.path(read_dir,run_name)

    drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))

    drivers$rank_shap_weight = rank(-drivers$weight_shap_total_mean)
    drivers$rank_grad_weight = rank(-abs(drivers$weight_grad_total_dir_mean))
    print(drivers[drivers$is_in_Pathway,])

    pathway_hallmark = openxlsx::read.xlsx(file.path('./resources/pathway', 'Gene_signature_list_paper_supp.xlsx'))
    tdf <- fread(file.path(read_dir,'driver_info_0.csv')) %>% dplyr::select(c('V1','weight_shap_total'))
    file_name = paste0('driver_info_',0,'.csv')
    df <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
    for (i in 1:9){
        file_name = paste0('driver_info_',i,'.csv')
        tdf <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
        df <- merge(df,tdf,by = 'V1',all = T,suffixes=c(i,i+1))

    }
    colnames(df) <- c('Gene',paste0('run',0:9))
    plot_df <- tidyr::gather(df, key = "variable", value = "value",-Gene)
    plot_df$pw = 'Other'
    if (any(drivers$is_in_FAM) & any(drivers$is_in_ROS)){
        plot_df[plot_df$Gene %in% pathway_hallmark$HALLMARK_REACTIVE_OXYGEN_SPECIES_PATHWAY,]$pw <- 'ROS'
        plot_df[plot_df$Gene %in% pathway_hallmark$HALLMARK_FATTY_ACID_METABOLISM,]$pw <- 'FAM'
        plot_df$pw <- factor(plot_df$pw ,levels = c('Other','ROS','FAM'))
        p <- ggplot(data = plot_df)+
            geom_boxplot(aes(x=variable,y=value,fill=pw))+
            theme_classic()
        ggsave(p,filename = paste0(run_name,'_dirver_in_pw.pdf'),height = 5,width = 6)
    }
    drivers$norm_shap <-  normalize(drivers$weight_shap_total_mean)
    ddf <- drivers[order(drivers$weight_shap_total_mean,decreasing = T),][1:10,] %>% as.data.frame()
    ddf$V1 <- factor(ddf$V1,levels = ddf$V1)
    p <- ggplot(ddf) +
        geom_bar(aes(x = V1, y = norm_shap),stat = "identity",fill=rgb(0.1,0.4,0.5,0.7))+
        theme_classic()
    ggsave(p,filename = paste0(run_name,'_dirver_top10.pdf'),height = 5,width = 6)
    
    tdf <- fread(file.path(read_dir,'driver_info_0.csv')) %>% dplyr::select(c('V1','weight_shap_total'))
    file_name = paste0('driver_info_',0,'.csv')
    df <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
    for (i in 1:9){
        file_name = paste0('driver_info_',i,'.csv')
        tdf <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
        df <- merge(df,tdf,by = 'V1',all = T,suffixes=c(i,i+1))

    }
    colnames(df) <- c('Gene',paste0('run',0:9))
    plot_df <- tidyr::gather(df, key = "variable", value = "value",-Gene)
    plot_df <- na.omit(plot_df)
    plot_df$value <- normalize(plot_df$value)

    gl <- ddf$V1
    tmp <- plot_df[plot_df$Gene %in% gl,]

    tmp$Gene <- factor(tmp$Gene,levels = rev(gl))
    p <- ggplot(tmp, aes(x = value, y = Gene, fill = Gene)) +
        ggridges::geom_density_ridges() +
        ggridges::theme_ridges() + 
        theme(legend.position = "none")
    ggsave(p,filename = paste0(run_name,'_dirver_top10_inrun.pdf'),height = 5,width = 5)
    
    gene <- bitr(drivers$V1, fromType="SYMBOL", toType=c("ENTREZID"), OrgDb="org.Hs.eg.db")
    gs <- drivers[order(weight_shap_total_mean,decreasing = T),]
    ags <- merge(gene,gs,by.x = 'SYMBOL',by.y='V1',all=F)
    gs <- ags[order(ags$weight_shap_total_mean,decreasing = T),]
    gs <- gs$weight_shap_total_mean
    names(gs) <- ags$ENTREZID
    
    m_t2g <- msigdbr(species = "Homo sapiens", category = "H") %>% 
                  dplyr::select(gs_name, entrez_gene)

    kk <- enrichKEGG(gene         = names(gs),
                     #keyType      = 'uniprot',
                     organism     = 'hsa',
                     pvalueCutoff = 0.05)
    #head(kk)
    em <- enricher(names(gs), 
               TERM2GENE=m_t2g,
              minGSSize    = 0,
                  #maxGSSize    = 500,
                  pvalueCutoff = 1,
                  #scoreType = "pos"
                  qvalueCutoff = 1,
                  #eps = eps,
                  #verbose      = FALSE
                  )
    draw_ridge(em,ags,name = paste0(run_name,'_HALLMARK'))
    draw_ridge(kk,ags,name = paste0(run_name,'_KEGG'))
    
}

run_name <- 'main_PC9_LUNG_run10_t0_t14_cyc'
pipe_n(run_name)

        V1 weight_shap_total_mean weight_shap_total_std
    <char>                  <num>                 <num>
1:   H2AFZ            0.001409551          0.0002377385
2:   PRDX1            0.005753293          0.0005948305
3:    NQO1            0.007189172          0.0005834166
4: ALDH3A1            0.001305538          0.0001966169
   weight_grad_total_dir_mean counts  is_tf is_in_FAM is_in_ROS is_in_Pathway
                        <num>  <int> <lgcl>    <lgcl>    <lgcl>        <lgcl>
1:               4.583457e-05     10  FALSE      TRUE     FALSE          TRUE
2:               1.307083e-04     10  FALSE     FALSE      TRUE          TRUE
3:               1.745988e-04     10  FALSE     FALSE      TRUE          TRUE
4:               4.354592e-07      4  FALSE      TRUE     FALSE          TRUE
   rank_shap_weight rank_grad_weight
              <num>            <num>
1:               37               41
2:                5                9
3:                3                3
4:               39               49

Warning message:
“Removed 408 rows containing non-finite outside the scale range
(`stat_boxplot()`).”
Picking joint bandwidth of 0.0311

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(drivers$V1, fromType = "SYMBOL", toType = c("ENTREZID"), :
“6.35% of input gene IDs are fail to map...”
Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.467

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.4

run_name <- 'main_PC9_LUNG_run10_t7_t14_cyc'
pipe_n(run_name)

        V1 weight_shap_total_mean weight_shap_total_std
    <char>                  <num>                 <num>
1:   PRDX1            0.003196059          0.0005124655
2:   H2AFZ            0.004075658          0.0005847643
3: ALDH3A1            0.004452039          0.0005462090
4:    NQO1            0.002075033          0.0002167071
   weight_grad_total_dir_mean counts  is_tf is_in_FAM is_in_ROS is_in_Pathway
                        <num>  <int> <lgcl>    <lgcl>    <lgcl>        <lgcl>
1:               0.0004087128     10  FALSE     FALSE      TRUE          TRUE
2:               0.0006475787     10  FALSE      TRUE     FALSE          TRUE
3:               0.0007624793     10  FALSE      TRUE     FALSE          TRUE
4:               0.0003687808      9  FALSE     FALSE      TRUE          TRUE
   rank_shap_weight rank_grad_weight
              <num>            <num>
1:               13               22
2:                8                8
3:                6                5
4:               23               24

Warning message:
“Removed 398 rows containing non-finite outside the scale range
(`stat_boxplot()`).”
Picking joint bandwidth of 0.021

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(drivers$V1, fromType = "SYMBOL", toType = c("ENTREZID"), :
“1.67% of input gene IDs are fail to map...”
Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.344

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.265

run_name <- 'main_PC9_LUNG_run10_t14_ncyc_cyc'
pipe_n(run_name)

       V1 weight_shap_total_mean weight_shap_total_std
   <char>                  <num>                 <num>
1:  H2AFZ           0.0015434791          0.0003817574
2:   JUNB           0.0016835371          0.0008096141
3:   SOD2           0.0002215576          0.0000000000
4: LGALS1           0.0001387697          0.0000000000
5:   PFKP           0.0002421256          0.0000000000
   weight_grad_total_dir_mean counts  is_tf is_in_FAM is_in_ROS is_in_Pathway
                        <num>  <int> <lgcl>    <lgcl>    <lgcl>        <lgcl>
1:               0.0015961908     10  FALSE      TRUE     FALSE          TRUE
2:              -0.0029814138      7   TRUE     FALSE      TRUE          TRUE
3:               0.0007589676      1  FALSE     FALSE      TRUE          TRUE
4:               0.0001830989      1  FALSE      TRUE     FALSE          TRUE
5:               0.0002091714      1  FALSE     FALSE      TRUE          TRUE
   rank_shap_weight rank_grad_weight
              <num>            <num>
1:               22               20
2:               20                9
3:               63               39
4:               72               65
5:               61               63

Warning message:
“Removed 666 rows containing non-finite outside the scale range
(`stat_boxplot()`).”
Picking joint bandwidth of 0.0387

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(drivers$V1, fromType = "SYMBOL", toType = c("ENTREZID"), :
“4.94% of input gene IDs are fail to map...”
Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.326

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.276

run_name <- 'main_PC9_LUNG_run10_t0_ncyc_cyc'
pipe_n(run_name)

Empty data.table (0 rows and 11 cols): V1,weight_shap_total_mean,weight_shap_total_std,weight_grad_total_dir_mean,counts,is_tf...

Picking joint bandwidth of 0.0387

'select()' returned 1:1 mapping between keys and columns

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.539

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.52

run_name <- 'main_PC9_LUNG_run10_t0_sen_res'
pipe_n(run_name)

Empty data.table (0 rows and 11 cols): V1,weight_shap_total_mean,weight_shap_total_std,weight_grad_total_dir_mean,counts,is_tf...

Picking joint bandwidth of 0.049

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(drivers$V1, fromType = "SYMBOL", toType = c("ENTREZID"), :
“3.85% of input gene IDs are fail to map...”
Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.588

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.592

run_name <- 'ex_PC9_LUNG_run10_ncyc_cyc'
pipe_n(run_name)

       V1 weight_shap_total_mean weight_shap_total_std
   <char>                  <num>                 <num>
1:   JUNB            0.001167002          0.0003537751
   weight_grad_total_dir_mean counts  is_tf is_in_FAM is_in_ROS is_in_Pathway
                        <num>  <int> <lgcl>    <lgcl>    <lgcl>        <lgcl>
1:              -0.0005070834     10   TRUE     FALSE      TRUE          TRUE
   rank_shap_weight rank_grad_weight
              <num>            <num>
1:                5               16

Picking joint bandwidth of 0.0559

'select()' returned 1:1 mapping between keys and columns

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.422

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.413

run_name <- 'ex_HCC827_LUNG_run10_ncyc_cyc'
pipe_n(run_name)

Empty data.table (0 rows and 11 cols): V1,weight_shap_total_mean,weight_shap_total_std,weight_grad_total_dir_mean,counts,is_tf...

Warning message:
“Removed 2 rows containing missing values or values outside the scale range
(`geom_bar()`).”
Picking joint bandwidth of 0.0206

'select()' returned 1:1 mapping between keys and columns

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.666

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.704

run_name <- 'main_PC9_LUNG_run10_t0_sen_res_strict'
pipe_n(run_name)

Empty data.table (0 rows and 11 cols): V1,weight_shap_total_mean,weight_shap_total_std,weight_grad_total_dir_mean,counts,is_tf...

Picking joint bandwidth of 0.0422

'select()' returned 1:1 mapping between keys and columns

Warning message in bitr(drivers$V1, fromType = "SYMBOL", toType = c("ENTREZID"), :
“3.33% of input gene IDs are fail to map...”
Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.539

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.465

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t0_t14_cyc'
read_dir <- file.path(read_dir,run_name)

drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(drivers)

drivers$rank_shap_weight = rank(-drivers$weight_shap_total_mean)
drivers$rank_grad_weight = rank(-abs(drivers$weight_grad_total_dir_mean))

drivers[drivers$is_in_Pathway,]

drivers %>% mutate(direction = ifelse(weight_grad_total_dir_mean >= 0,1,-1)) %>% filter(counts >=10)

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'ex_PC9_LUNG_run10_ncyc_cyc'
read_dir <- file.path(read_dir,run_name)

drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(drivers)

drivers$rank_shap_weight = rank(-drivers$weight_shap_total_mean)
drivers$rank_grad_weight = rank(-abs(drivers$weight_grad_total_dir_mean))

drivers[drivers$is_in_Pathway,]

drivers[order(weight_shap_total_mean,decreasing = T),]

tdf <- fread(file.path(read_dir,'driver_info_0.csv')) %>% dplyr::select(c('V1','weight_shap_total'))

file_name = paste0('driver_info_',0,'.csv')
df <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
for (i in 1:9){
    file_name = paste0('driver_info_',i,'.csv')
    tdf <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
    df <- merge(df,tdf,by = 'V1',all = T,suffixes=c(i,i+1))
    
}
colnames(df) <- c('Gene',paste0('run',0:9))

plot_df <- tidyr::gather(df, key = "variable", value = "value",-Gene)

plot_df

gl <- drivers[order(weight_shap_total_mean,decreasing = T),]$V1[1:10]

tmp <- plot_df[plot_df$Gene %in% gl,]

tmp$Gene <- factor(tmp$Gene,levels = rev(gl))

gl

ridge_p <- ggplot(tmp, aes(x = value, y = Gene, fill = Gene)) +
  ggridges::geom_density_ridges() +
  ggridges::theme_ridges() + 
  ggsci::scale_fill_npg()+
xlab('SHAP weight')+
ylab('Driver genes')+
ggtitle("Weight through model with different seeds")+
scale_color_manual(values = c('In two pathway'= '#559073FF','Out of two pathway'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   legend.position = 'none',
   panel.grid = element_blank()
      
)
ridge_p

Picking joint bandwidth of 0.00019

Warning message:
“Removed 2 rows containing non-finite outside the scale range
(`stat_density_ridges()`).”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

ggsave(plot = ridge_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/ext_PC9_cyc_ridge_p.pdf',
       width =16/1.5, height =16/1.5)
ggsave(plot = ridge_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/ext_PC9_cyc_ridge_p.png',
       width =16/1.5, height =16/1.5)

Picking joint bandwidth of 0.00019

Warning message:
“Removed 2 rows containing non-finite outside the scale range
(`stat_density_ridges()`).”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”
Picking joint bandwidth of 0.00019

Warning message:
“Removed 2 rows containing non-finite outside the scale range
(`stat_density_ridges()`).”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

gene <- bitr(drivers$V1, fromType="SYMBOL", toType=c("ENTREZID"), OrgDb="org.Hs.eg.db")


'select()' returned 1:1 mapping between keys and columns

gs <- drivers[order(weight_shap_total_mean,decreasing = T),]
ags <- merge(gene,gs,by.x = 'SYMBOL',by.y='V1',all=F)
gs <- ags[order(ags$weight_shap_total_mean,decreasing = T),]
gs <- gs$weight_shap_total_mean
names(gs) <- ags$ENTREZID

em <- GSEA(gs*1000, 
           TERM2GENE=m_t2g,
          minGSSize    = 0,
              #maxGSSize    = 500,
              pvalueCutoff = 1,
              scoreType = "pos"
              #qvalueCutoff = 1,
              #eps = eps,
              #verbose      = FALSE
              )
head(em)

preparing geneSet collections...

GSEA analysis...

leading edge analysis...

done...

em@result

em <- enricher(names(gs), 
           TERM2GENE=m_t2g,
          minGSSize    = 0,
              #maxGSSize    = 500,
              pvalueCutoff = 1,
              #scoreType = "pos"
              qvalueCutoff = 1,
              #eps = eps,
              #verbose      = FALSE
              )
head(em)

em@result

m_t2g <- msigdbr(species = "Homo sapiens", category = "H") %>% 
  dplyr::select(gs_name, entrez_gene)

m_t2g$gs_name <- m_t2g$gs_name %>% 
    stringr::str_replace_all(pattern = 'HALLMARK_',replacement = '') %>%
    stringr::str_replace_all(pattern = '_',replacement = ' ') %>%
    stringr::str_to_title()

kk <- enrichKEGG(gene         = names(gs),
                 #keyType      = 'uniprot',
                 organism     = 'hsa',
                 pvalueCutoff = 0.05)
#head(kk)
em <- enricher(names(gs), 
           TERM2GENE=m_t2g,
          minGSSize    = 0,
              #maxGSSize    = 500,
              pvalueCutoff = 1,
              #scoreType = "pos"
              qvalueCutoff = 1,
              #eps = eps,
              #verbose      = FALSE
              )

high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
gs_name <- em@result$Description
high_mean_ls <-c()

for (i in 1:nrow(em@result)){
    if (i==1){
        
        ls <- em@geneSets[em@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))
        
    }else{
        
    ls <- em@geneSets[em@result[i,'ID']]
    where <- which(high_df$ENTREZID %in% ls[[1]])
    tmp <- high_df[where,]
    tmp$gs <- gs_name[i]
    tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
    high_plot_df <- rbind(high_plot_df,tmp)
    high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))
        
    }
}

high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

length(table(high_plot_df$gs))
table(high_plot_df$gs)

                     Adipogenesis                 Androgen Response 
                                3                                 4 
                  Apical Junction                         Apoptosis 
                                1                                 3 
                      Coagulation                        Complement 
                                1                                 1 
                      E2f Targets Epithelial Mesenchymal Transition 
                                3                                 4 
          Estrogen Response Early            Estrogen Response Late 
                                6                                 3 
                   G2m Checkpoint                        Glycolysis 
                                5                                 1 
               Hedgehog Signaling                   Heme Metabolism 
                                1                                 2 
                          Hypoxia               Il2 Stat5 Signaling 
                                6                                 4 
          Il6 Jak Stat3 Signaling             Inflammatory Response 
                                1                                 1 
        Interferon Gamma Response                 Kras Signaling Up 
                                1                                 2 
                  Mitotic Spindle                  Mtorc1 Signaling 
                                3                                 3 
                   Myc Targets V1                    Myc Targets V2 
                                1                                 1 
                       Myogenesis                   Notch Signaling 
                                4                                 2 
                      P53 Pathway               Pancreas Beta Cells 
                                6                                 1 
                       Peroxisome           Pi3k Akt Mtor Signaling 
                                1                                 4 
  Reactive Oxygen Species Pathway                Tgf Beta Signaling 
                                1                                 3 
          Tnfa Signaling Via Nfkb                    Uv Response Dn 
                                9                                 1 
                   Uv Response Up             Xenobiotic Metabolism 
                                3                                 3

add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
add

high_plot_df <- rbind(high_plot_df,add,add)
length(table(high_plot_df$gs))
table(high_plot_df$gs)

                     Adipogenesis                 Androgen Response 
                                3                                 4 
                  Apical Junction                         Apoptosis 
                                3                                 3 
                      Coagulation                        Complement 
                                3                                 3 
                      E2f Targets Epithelial Mesenchymal Transition 
                                3                                 4 
          Estrogen Response Early            Estrogen Response Late 
                                6                                 3 
                   G2m Checkpoint                        Glycolysis 
                                5                                 3 
               Hedgehog Signaling                   Heme Metabolism 
                                3                                 6 
                          Hypoxia               Il2 Stat5 Signaling 
                                6                                 4 
          Il6 Jak Stat3 Signaling             Inflammatory Response 
                                3                                 3 
        Interferon Gamma Response                 Kras Signaling Up 
                                3                                 6 
                  Mitotic Spindle                  Mtorc1 Signaling 
                                3                                 3 
                   Myc Targets V1                    Myc Targets V2 
                                3                                 3 
                       Myogenesis                   Notch Signaling 
                                4                                 6 
                      P53 Pathway               Pancreas Beta Cells 
                                6                                 3 
                       Peroxisome           Pi3k Akt Mtor Signaling 
                                3                                 4 
  Reactive Oxygen Species Pathway                Tgf Beta Signaling 
                                3                                 3 
          Tnfa Signaling Via Nfkb                    Uv Response Dn 
                                9                                 3 
                   Uv Response Up             Xenobiotic Metabolism 
                                3                                 3

high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
head(high_plot_df)

high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序

colnames(high_plot_df) <- c('gs','Weight','mean')

pRidge_H <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = 'Hallmark',fill = 'Log10 mean of weight') +
    xlab('SHAP weight')+
    ylab('Gene set')+
  scale_y_discrete(labels=function(x){stringr::str_wrap(x, width=30)})+
  scale_fill_gradientn(name = "Log10 mean \nof weight",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
plot.background = element_rect(fill = "transparent", color = NA), # bg of the plot
panel.background = element_rect(fill = "transparent"), # bg of the panel
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank(), # get rid of minor grid
legend.key.size = unit(20,'points'),
legend.text = element_text(face = 'italic',size=18),
#legend.title = element_text(face = 'bold',size=18), 
legend.title = element_text(face = 'bold',size=18),
legend.position = 'right'
       )

pRidge_H

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.453

png('weight_pRidge_all_meancolor1.png',height = 500*5,width = 600*5,res=400)
    pRidge
dev.off()

Picking joint bandwidth of 0.322

ggsave(plot = pRidge_H,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/ext_PC9_cyc_pRidge_H.pdf',
       width =16/1.5, height =24/1.5)
ggsave(plot = pRidge_H,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/ext_PC9_cyc_pRidge_H.png',
       width =16/1.5, height =24/1.5)

Picking joint bandwidth of 0.453

Picking joint bandwidth of 0.453

high_df <- ags[order(ags$weight_shap_total_mean,decreasing = T),] %>% dplyr::select(c('ENTREZID','weight_shap_total_mean'))
gs_name <- kk@result[1:30,]$Description
high_mean_ls <-c()

for (i in 1:nrow(kk@result[1:30,])){
    if (i==1){
        
        ls <- kk@geneSets[kk@result[i,'ID']]
        where <- which(high_df$ENTREZID %in% ls[[1]])
        tmp <- high_df[where,]
        tmp$gs <- gs_name[i]
        high_plot_df <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
        high_mean_ls <- c(high_mean_ls,mean(high_plot_df$weight_shap_total_mean,na.rm = T))
        
    }else{
        
    ls <- kk@geneSets[kk@result[i,'ID']]
    where <- which(high_df$ENTREZID %in% ls[[1]])
    tmp <- high_df[where,]
    tmp$gs <- gs_name[i]
    tmp <- tmp %>% dplyr::select(c('weight_shap_total_mean','gs'))
    high_plot_df <- rbind(high_plot_df,tmp)
    high_mean_ls <- c(high_mean_ls,mean(tmp$weight_shap_total_mean,,na.rm = T))
        
    }
}

high_mean_df <- data.frame(gs=gs_name,mean=high_mean_ls)

add <- high_plot_df[high_plot_df$gs %in% names(which(table(high_plot_df$gs) == 1 | table(high_plot_df$gs) == 2)),]
high_plot_df <- rbind(high_plot_df,add,add)
high_plot_df <- merge(high_plot_df,high_mean_df,by='gs',all.x=T)
high_mean_df <- high_mean_df[order(high_mean_df$mean,decreasing=T),]
high_plot_df$gs<-factor(high_plot_df$gs,levels=rev(high_mean_df$gs))#排序
colnames(high_plot_df) <- c('gs','Weight','mean')

pRidge_K <- ggplot(high_plot_df,aes(x = scale(Weight), y = gs, fill = log(mean))) +
  ggridges::geom_density_ridges_gradient(scale = 3,size=0.6) +
  labs(title = 'KEGG',fill = 'Log10 mean of weight') +
    xlab('SHAP weight')+
    ylab('Gene set')+
  scale_y_discrete(labels=function(x){stringr::str_wrap(x, width=30)})+
  scale_fill_gradientn(name = "Log10 mean \nof weight",colors=c("#AFD1E6","#C3CFC6",'#E7B46A',"#F6A015"),values=c(0,0.4,0.6,2))+
  theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
plot.background = element_rect(fill = "transparent", color = 'white'), # bg of the plot
panel.background = element_rect(fill = "transparent"), # bg of the panel
panel.grid.major = element_blank(), # get rid of major grid
panel.grid.minor = element_blank(), # get rid of minor grid
legend.key.size = unit(20,'points'),
legend.text = element_text(face = 'italic',size=18),
#legend.title = element_text(face = 'bold',size=18), 
legend.title = element_text(face = 'bold',size=18),
legend.position = 'right'
       )

pRidge_K

Warning message in ggridges::geom_density_ridges_gradient(scale = 3, size = 0.6):
“Ignoring unknown parameters: `size`”
Picking joint bandwidth of 0.413

ggsave(plot = pRidge_K,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/ext_PC9_cyc_pRidge_K.pdf',
       width =16/1.5, height =24/1.5)
ggsave(plot = pRidge_K,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/ext_PC9_cyc_pRidge_K.png',
       width =16/1.5, height =24/1.5)

Picking joint bandwidth of 0.413

Picking joint bandwidth of 0.413

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t14_ncyc_cyc'
read_dir <- file.path(read_dir,run_name)

t14_drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(t14_drivers)

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t0_ncyc_cyc'
read_dir <- file.path(read_dir,run_name)

t0_drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(t0_drivers)

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t0_t14_cyc'
read_dir <- file.path(read_dir,run_name)

t0_14_drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(t0_14_drivers)

head(drivers)

intersect(t14_drivers$V1, drivers$V1)

library(ggvenn)

Loading required package: grid

a <- list(T14 = t14_drivers$V1,
          EXT = drivers$V1,
           T0 = t0_drivers$V1,
           'T0-14' = t0_14_drivers$V1)
p1=ggvenn(a, c("T14", "EXT","T0",'T0-14')) 
p1

ggsave(plot = p1,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/cyc_venn.pdf',
       width =16/1.5, height =16/1.5)
ggsave(plot = p1,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/cyc_venn.png',
       width =16/1.5, height =16/1.5)

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t0_sen_res'
read_dir <- file.path(read_dir,run_name)

drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(drivers)

drivers$rank_shap_weight = rank(-drivers$weight_shap_total_mean)
drivers$rank_grad_weight = rank(-abs(drivers$weight_grad_total_dir_mean))

drivers[order(drivers$weight_shap_total_mean,decreasing = T),]

read_dir

tdf <- fread(file.path(read_dir,'driver_info_0.csv')) %>% dplyr::select(c('V1','weight_shap_total'))

file_name = paste0('driver_info_',0,'.csv')
df <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
for (i in 1:9){
    file_name = paste0('driver_info_',i,'.csv')
    tdf <- fread(file.path(read_dir,file_name)) %>% dplyr::select(c('V1','weight_shap_total'))
    df <- merge(df,tdf,by = 'V1',all = T,suffixes=c(i,i+1))
    
}
colnames(df) <- c('Gene',paste0('run',0:9))

plot_df <- tidyr::gather(df, key = "variable", value = "value",-Gene)

plot_df

gl <- drivers[order(weight_shap_total_mean,decreasing = T),]$V1[1:10]

tmp <- plot_df[plot_df$Gene %in% gl,]

tmp$Gene <- factor(tmp$Gene,levels = rev(gl))

gl

ridge_p <- ggplot(tmp, aes(x = value, y = Gene, fill = Gene)) +
  ggridges::geom_density_ridges() +
  ggridges::theme_ridges() + 
  ggsci::scale_fill_npg()+
xlab('SHAP weight')+
ylab('Driver genes')+
ggtitle("Weight through model with different seeds")+
scale_color_manual(values = c('In two pathway'= '#559073FF','Out of two pathway'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5,hjust = 0.5),
    axis.title.y = element_text(vjust = 5,hjust = 0.5),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(vjust = 0.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   legend.position = 'none',
   panel.grid = element_blank()
      
)
ridge_p

Picking joint bandwidth of 0.000273

Warning message:
“Removed 6 rows containing non-finite outside the scale range
(`stat_density_ridges()`).”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

ggsave(plot = ridge_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/sen_res_ridge_p.pdf',
       width =16/1.5, height =16/1.5)
ggsave(plot = ridge_p,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/sen_res_ridge_p.png',
       width =16/1.5, height =16/1.5)

Picking joint bandwidth of 0.000273

Warning message:
“Removed 6 rows containing non-finite outside the scale range
(`stat_density_ridges()`).”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”
Picking joint bandwidth of 0.000273

Warning message:
“Removed 6 rows containing non-finite outside the scale range
(`stat_density_ridges()`).”
Warning message:
“No shared levels found between `names(values)` of the manual scale and the
data's colour values.”

drivers_exp <- fread(file.path(read_dir,'driver_summary_shap_total_addexp.csv'))

head(drivers_exp)

GDSC_exp <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/GDSC/Cell_line_RMA_proc_basalExp.txt')

head(GDSC_exp)

GDSC_compounds <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/GDSC/screened_compounds_rel_8.5.csv')

GDSC_compounds

GDSC_cellline <- openxlsx::read.xlsx('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/GDSC/Cell_Lines_Details.xlsx')

head(GDSC_cellline)

GDSC_drug1 <- openxlsx::read.xlsx('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/GDSC/GDSC1_fitted_dose_response_27Oct23.xlsx')

GDSC_drug1

GDSC_drug2 <- openxlsx::read.xlsx('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/GDSC/GDSC2_fitted_dose_response_27Oct23.xlsx')

GDSC_drug2

any(GDSC_drug1$DRUG_NAME == 'Osimertinib')

any(GDSC_drug2$DRUG_NAME == 'Osimertinib')

GDSC_drug2 %>% dplyr::filter(GDSC_drug2$DRUG_NAME == 'Osimertinib')

GDSC_cellline %>% dplyr::filter(GDSC_cellline$Gene.Expression == 'Y')

luad_Osimertinib <- GDSC_drug2 %>% dplyr::filter(GDSC_drug2$COSMIC_ID %in% substring(colnames(GDSC_exp),6)) %>%
    dplyr::filter(DRUG_NAME == 'Osimertinib') %>%
    dplyr::filter(TCGA_DESC == 'LUAD') 

luad_Osimertinib

luad_Osimertinib_exp <- GDSC_exp %>% dplyr::select(c(1,which(substring(colnames(GDSC_exp),6) %in% luad_Osimertinib$COSMIC_ID)))
head(luad_Osimertinib_exp)

luad_Osimertinib_exp_SLC1A5 <-  luad_Osimertinib_exp%>% dplyr::filter(GENE_SYMBOLS == 'SLC1A5') %>% t() %>% as.data.frame()

luad_Osimertinib_exp_SLC1A5 <- luad_Osimertinib_exp_SLC1A5 %>% mutate(COSMIC_ID = substring(rownames(luad_Osimertinib_exp_SLC1A5),6))
luad_Osimertinib_exp_SLC1A5 <- luad_Osimertinib_exp_SLC1A5[2:nrow(luad_Osimertinib_exp_SLC1A5),] %>% apply(2,as.numeric)
colnames(luad_Osimertinib_exp_SLC1A5) <- c('SLC1A5','COSMIC_ID')

luad_Osimertinib_exp_SLC1A5

cor_df <- luad_Osimertinib %>% 
dplyr::select(c('COSMIC_ID','LN_IC50','AUC')) %>% 
merge(luad_Osimertinib_exp_SLC1A5,by = 'COSMIC_ID',all = T)

head(cor_df)

cor.test(cor_df$LN_IC50,cor_df$SLC1A5)

	Pearson's product-moment correlation

data:  cor_df$LN_IC50 and cor_df$SLC1A5
t = 0.77573, df = 59, p-value = 0.441
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 -0.1552687  0.3436072
sample estimates:
      cor 
0.1004808

drivers$V1

luad_Osimertinib_exp_m <-  luad_Osimertinib_exp%>% dplyr::filter(GENE_SYMBOLS %in% drivers$V1) %>% as.data.frame()

rn <- luad_Osimertinib_exp_m$GENE_SYMBOLS
luad_Osimertinib_exp_m <- luad_Osimertinib_exp_m[,2:ncol(luad_Osimertinib_exp_m)]
rownames(luad_Osimertinib_exp_m) <- rn
colnames(luad_Osimertinib_exp_m) <- substring(colnames(luad_Osimertinib_exp_m),6)
luad_Osimertinib_exp_m

ComplexHeatmap::Heatmap(luad_Osimertinib_exp_m)

Warning message:
“The input is a data frame-like object, convert it to a matrix.”

luad_Osimertinib_exp_TGM2 <-  luad_Osimertinib_exp%>% dplyr::filter(GENE_SYMBOLS == 'TGM2') %>% t() %>% as.data.frame()
luad_Osimertinib_exp_TGM2 <- luad_Osimertinib_exp_TGM2 %>% mutate(COSMIC_ID = substring(rownames(luad_Osimertinib_exp_TGM2),6))
luad_Osimertinib_exp_TGM2 <- luad_Osimertinib_exp_TGM2[2:nrow(luad_Osimertinib_exp_TGM2),] %>% apply(2,as.numeric)
colnames(luad_Osimertinib_exp_TGM2) <- c('TGM2','COSMIC_ID')

cor_df <- luad_Osimertinib %>% 
dplyr::select(c('COSMIC_ID','LN_IC50','AUC')) %>% 
merge(luad_Osimertinib_exp_TGM2,by = 'COSMIC_ID',all = T)

head(cor_df)

cor.test(cor_df$LN_IC50,cor_df$TGM2)
cor.test(cor_df$AUC,cor_df$TGM2)

	Pearson's product-moment correlation

data:  cor_df$LN_IC50 and cor_df$TGM2
t = -0.11523, df = 59, p-value = 0.9087
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 -0.2658161  0.2377193
sample estimates:
        cor 
-0.01499935

	Pearson's product-moment correlation

data:  cor_df$AUC and cor_df$TGM2
t = -0.4178, df = 59, p-value = 0.6776
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 -0.3020029  0.2002469
sample estimates:
        cor 
-0.05431266

dri10 <- drivers %>% dplyr::filter(counts == 10)

luad_Osimertinib_exp_m <-  luad_Osimertinib_exp%>% dplyr::filter(GENE_SYMBOLS %in% dri10$V1) %>% as.data.frame()

rn <- luad_Osimertinib_exp_m$GENE_SYMBOLS
luad_Osimertinib_exp_m <- luad_Osimertinib_exp_m[,2:ncol(luad_Osimertinib_exp_m)]
rownames(luad_Osimertinib_exp_m) <- rn
colnames(luad_Osimertinib_exp_m) <- substring(colnames(luad_Osimertinib_exp_m),6)
luad_Osimertinib_exp_m

ComplexHeatmap::Heatmap(luad_Osimertinib_exp_m)

Warning message:
“The input is a data frame-like object, convert it to a matrix.”

Osimertinib <- GDSC_drug2 %>% dplyr::filter(GDSC_drug2$COSMIC_ID %in% substring(colnames(GDSC_exp),6)) %>%
    dplyr::filter(DRUG_NAME == 'Osimertinib') 

Osimertinib

ComplexHeatmap::Heatmap(normalize(luad_Osimertinib[,c('LN_IC50')]))

ComplexHeatmap::Heatmap(normalize(Osimertinib[,c('LN_IC50')]))

ComplexHeatmap::Heatmap(normalize(luad_Osimertinib[,c('AUC')]))

ComplexHeatmap::Heatmap(normalize(Osimertinib[,c('AUC')]))

用权重加权基因算得分 只看正 只看负 加载一起

和药物反应相关高的基因与driver找关联

提高driver范围，在所以癌症中做

跨组学去找CNV

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t0_sen_res'
read_dir <- file.path(read_dir,run_name)

drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))
head(drivers)

drivers

luad_Osimertinib_exp_m <-  luad_Osimertinib_exp%>% dplyr::filter(GENE_SYMBOLS %in% drivers$V1) %>% as.data.frame()

rn <- luad_Osimertinib_exp_m$GENE_SYMBOLS
luad_Osimertinib_exp_m <- luad_Osimertinib_exp_m[,2:ncol(luad_Osimertinib_exp_m)]
rownames(luad_Osimertinib_exp_m) <- rn
colnames(luad_Osimertinib_exp_m) <- substring(colnames(luad_Osimertinib_exp_m),6)
luad_Osimertinib_exp_m

luad_Osimertinib_exp_m$V1 = rownames(luad_Osimertinib_exp_m)

score_df <- merge(luad_Osimertinib_exp_m,drivers,by = 'V1',all = F)
score_df

FUN1 <- function(x){
    sum(x*score_df$weight_shap_total_mean)
    #sum(x)
}
score <- apply(score_df[,2:61],MARGIN  = 2,FUN = FUN1)

score

drug_res <- luad_Osimertinib %>% 
dplyr::select(c('COSMIC_ID','LN_IC50','AUC')) %>% filter(COSMIC_ID %in% names(score))
head(drug_res)

drug_res$score = score[as.character(drug_res$COSMIC_ID)]

#cor.test(drug_res$LN_IC50,drug_res$score,alternative = 'less',method =  'pearson')
#cor.test(drug_res$LN_IC50,drug_res$score,method =  'kendall')
cor.test(drug_res$LN_IC50,drug_res$score,alternative = 'less',method =  'spearman')
cor.test(drug_res$AUC,drug_res$score,alternative = 'less',method =  'spearman')

	Spearman's rank correlation rho

data:  drug_res$LN_IC50 and drug_res$score
S = 45740, p-value = 0.01831
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.2709086

	Spearman's rank correlation rho

data:  drug_res$AUC and drug_res$score
S = 45068, p-value = 0.02606
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.2522367

?cor.test

normalize <- function(v) {
  (v - min(v)) / (max(v) - min(v))
}
FUN2 <- function(x){
    sum(x*normalize(score_df$weight_shap_total_mean))
    #sum(x)
}
FUN3 <- function(x){
    mean(x*normalize(score_df$weight_shap_total_mean))
    #sum(x)
}
score <- apply(score_df[,2:61],MARGIN  = 2,FUN = FUN2)

drug_res$score2 = score[as.character(drug_res$COSMIC_ID)]

cor.test(drug_res$LN_IC50,drug_res$score2,alternative = 'less',method =  'spearman')
cor.test(drug_res$AUC,drug_res$score2,alternative = 'less',method =  'spearman')

	Spearman's rank correlation rho

data:  drug_res$LN_IC50 and drug_res$score2
S = 45936, p-value = 0.01645
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.2763545

	Spearman's rank correlation rho

data:  drug_res$AUC and drug_res$score2
S = 44496, p-value = 0.03461
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.2363434

FUN3 <- function(x){
    mean(x*normalize(score_df$weight_shap_total_mean))
    #sum(x)
}
score <- apply(score_df[,2:61],MARGIN  = 2,FUN = FUN3)

drug_res$score3 = score[as.character(drug_res$COSMIC_ID)]

cor.test(drug_res$LN_IC50,drug_res$score3,alternative = 'less',method =  'spearman')
cor.test(drug_res$AUC,drug_res$score3,alternative = 'less',method =  'spearman')

	Spearman's rank correlation rho

data:  drug_res$LN_IC50 and drug_res$score3
S = 45936, p-value = 0.01645
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.2763545

	Spearman's rank correlation rho

data:  drug_res$AUC and drug_res$score3
S = 44496, p-value = 0.03461
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.2363434

drug_res

drivers$directions = drivers$weight_grad_total_dir_mean >= 0

drivers_pos = drivers %>% filter(drivers$directions)
drivers_neg = drivers %>% filter(!drivers$directions)

score_df <- merge(luad_Osimertinib_exp_m,drivers_pos,by = 'V1',all = F)
score <- apply(score_df[,2:61],MARGIN  = 2,FUN = FUN1)

drug_res <- luad_Osimertinib %>% 
dplyr::select(c('COSMIC_ID','LN_IC50','AUC')) %>% filter(COSMIC_ID %in% names(score))
drug_res$score = score[as.character(drug_res$COSMIC_ID)]

cor.test(drug_res$LN_IC50,drug_res$score,alternative = 'less',method =  'spearman')
cor.test(drug_res$AUC,drug_res$score,alternative = 'less',method =  'spearman')

	Spearman's rank correlation rho

data:  drug_res$LN_IC50 and drug_res$score
S = 50644, p-value = 0.0006783
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.4071687

	Spearman's rank correlation rho

data:  drug_res$AUC and drug_res$score
S = 49744, p-value = 0.001378
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.3821617

score_df <- merge(luad_Osimertinib_exp_m,drivers_neg,by = 'V1',all = F)
score <- apply(score_df[,2:61],MARGIN  = 2,FUN = FUN1)

drug_res <- luad_Osimertinib %>% 
dplyr::select(c('COSMIC_ID','LN_IC50','AUC')) %>% filter(COSMIC_ID %in% names(score))
drug_res$score = score[as.character(drug_res$COSMIC_ID)]

cor.test(drug_res$LN_IC50,drug_res$score,alternative = 'less',method =  'spearman')
cor.test(drug_res$AUC,drug_res$score,alternative = 'less',method =  'spearman')

	Spearman's rank correlation rho

data:  drug_res$LN_IC50 and drug_res$score
S = 37518, p-value = 0.3734
alternative hypothesis: true rho is less than 0
sample estimates:
        rho 
-0.04245624

	Spearman's rank correlation rho

data:  drug_res$AUC and drug_res$score
S = 37770, p-value = 0.3534
alternative hypothesis: true rho is less than 0
sample estimates:
        rho 
-0.04945818

FUN4 <- function(x){
    mean(x*score_df$weight_shap_total_mean)
    #sum(x)
}

score_df <- merge(luad_Osimertinib_exp_m,drivers_pos,by = 'V1',all = F)
score <- apply(score_df[,2:61],MARGIN  = 2,FUN = FUN4)

drug_res <- luad_Osimertinib %>% 
dplyr::select(c('COSMIC_ID','LN_IC50','AUC')) %>% filter(COSMIC_ID %in% names(score))
drug_res$score = score[as.character(drug_res$COSMIC_ID)]

cor.test(drug_res$LN_IC50,drug_res$score,alternative = 'less',method =  'spearman')
cor.test(drug_res$AUC,drug_res$score,alternative = 'less',method =  'spearman')

	Spearman's rank correlation rho

data:  drug_res$LN_IC50 and drug_res$score
S = 50644, p-value = 0.0006783
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.4071687

	Spearman's rank correlation rho

data:  drug_res$AUC and drug_res$score
S = 49744, p-value = 0.001378
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.3821617

drivers$directions_cal = as.numeric(drivers$directions)
drivers[!drivers$directions,]$directions_cal = -1

drivers

FUN5 <- function(x){
    sum(x*score_df$weight_shap_total_mean*score_df$directions_cal)
    #sum(x)
}
score_df <- merge(luad_Osimertinib_exp_m,drivers,by = 'V1',all = F)
score <- apply(score_df[,2:61],MARGIN  = 2,FUN = FUN5)

drug_res <- luad_Osimertinib %>% 
dplyr::select(c('COSMIC_ID','LN_IC50','AUC')) %>% filter(COSMIC_ID %in% names(score))
drug_res$score = score[as.character(drug_res$COSMIC_ID)]

cor.test(drug_res$LN_IC50,drug_res$score,alternative = 'less',method =  'spearman')
cor.test(drug_res$AUC,drug_res$score,alternative = 'less',method =  'spearman')

	Spearman's rank correlation rho

data:  drug_res$LN_IC50 and drug_res$score
S = 47080, p-value = 0.008474
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.3081412

	Spearman's rank correlation rho

data:  drug_res$AUC and drug_res$score
S = 46064, p-value = 0.01532
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.2799111

CCLE_exp <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/CCLE/CCLE_DepMap_18Q1_RNAseq_RPKM_20180214.gct')

CCLE_exp

CCLE_info <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/CCLE/sample_info.csv')

CCLE_info

table(CCLE_info$tumor_type)

                              AML          Bladder             Bone 
               1               10               20                3 
          Breast         Cervical            Colon      Endometrial 
              26                1               25               14 
      Esophageal          Ewing's          Gastric     Glioblastoma 
              10                4               11               20 
          glioma           Glioma    Head and Neck           Kidney 
               1                9               12               17 
           Liver             Lung         Lymphoma  Medulloblastoma 
              13               48                8                7 
    Mesothelioma          Myeloma    Neuroblastoma     Osteosarcoma 
               1                7               15                5 
           Other          Ovarian         Pancreas         Rhabdoid 
               9               31               22                3 
             RMS          Sarcoma             Skin Synovial Sarcoma 
               6                1               29                2 
           T-ALL          Thyroid 
               2                1

CCLE_drug <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/CCLE/CCLE_NP24.2009_Drug_data_2015.02.24.csv')

CCLE_drug

any(CCLE_drug$Compound == 'Osimertinib')

table(CCLE_drug$Compound)

      17-AAG       AEW541      AZD0530      AZD6244    Erlotinib   Irinotecan 
         503          503          504          503          503          317 
    L-685458    Lapatinib       LBW242    Nilotinib     Nutlin-3   Paclitaxel 
         491          504          503          420          504          503 
Panobinostat   PD-0325901   PD-0332991    PF2341066   PHA-665752      PLX4720 
         500          504          434          504          503          496 
      RAF265    Sorafenib       TAE684       TKI258    Topotecan      ZD-6474 
         460          503          504          504          504          496

table(CCLE_drug$Target)

  ABL   ALK c-MET  CDK4  EGFR  FGFR    GS  HDAC HSP90 IGF1R  MDM2   MEK   RAF 
  924   504  1007   434  1503   504   491   500   503   503   504  1007   956 
  RTK  TOP1 TUBB1  XIAP 
  503   821   503   503

CCLE_drug %>% filter(CCLE_drug$Target == 'EGFR') %>% dplyr::select(Compound) %>% table()

Compound
Erlotinib Lapatinib   ZD-6474 
      503       504       496

CCLE_drug_info <- readxl::read_excel('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/CCLE/CCLE_GNF_data_090613.xls')

CCLE_drug_info

select_cl <- CCLE_drug %>% 
    filter(CCLE_drug$Target == 'EGFR') %>% 
    dplyr::select('CCLE Cell Line Name') %>% 
    t() %>% c()

CCLE_exp %>% dplyr::select(c('Description',select_cl))

Warning message:
“Using an external vector in selections was deprecated in tidyselect 1.1.0.
ℹ Please use `all_of()` or `any_of()` instead.
  # Was:
  data %>% select(select_cl)

  # Now:
  data %>% select(all_of(select_cl))

See <https://tidyselect.r-lib.org/reference/faq-external-vector.html>.”

Error in `dplyr::select()`:
! Can't subset columns that don't exist.
✖ Columns `1321N1_CENTRAL_NERVOUS_SYSTEM`, `AZ521_STOMACH`, `BGC823_STOMACH`, `C3A_LIVER`, `CHL1_SKIN`, etc. don't exist.
Traceback:

1. CCLE_exp %>% dplyr::select(c("Description", select_cl))
2. dplyr::select(., c("Description", select_cl))
3. select.data.frame(., c("Description", select_cl))
4. tidyselect::eval_select(expr(c(...)), data = .data, error_call = error_call)
5. eval_select_impl(data, names(data), as_quosure(expr, env), include = include, 
 .     exclude = exclude, strict = strict, name_spec = name_spec, 
 .     allow_rename = allow_rename, allow_empty = allow_empty, allow_predicates = allow_predicates, 
 .     error_call = error_call, )
6. with_subscript_errors(out <- vars_select_eval(vars, expr, strict = strict, 
 .     data = x, name_spec = name_spec, uniquely_named = uniquely_named, 
 .     allow_rename = allow_rename, allow_empty = allow_empty, allow_predicates = allow_predicates, 
 .     type = type, error_call = error_call), type = type)
7. try_fetch(expr, vctrs_error_subscript = function(cnd) {
 .     cnd$subscript_action <- subscript_action(type)
 .     cnd$subscript_elt <- "column"
 .     cnd_signal(cnd)
 . })
8. withCallingHandlers(expr, condition = function(cnd) {
 .     {
 .         .__handler_frame__. <- TRUE
 .         .__setup_frame__. <- frame
 .         if (inherits(cnd, "message")) {
 .             except <- c("warning", "error")
 .         }
 .         else if (inherits(cnd, "warning")) {
 .             except <- "error"
 .         }
 .         else {
 .             except <- ""
 .         }
 .     }
 .     while (!is_null(cnd)) {
 .         if (inherits(cnd, "vctrs_error_subscript")) {
 .             out <- handlers[[1L]](cnd)
 .             if (!inherits(out, "rlang_zap")) 
 .                 throw(out)
 .         }
 .         inherit <- .subset2(.subset2(cnd, "rlang"), "inherit")
 .         if (is_false(inherit)) {
 .             return()
 .         }
 .         cnd <- .subset2(cnd, "parent")
 .     }
 . })
9. vars_select_eval(vars, expr, strict = strict, data = x, name_spec = name_spec, 
 .     uniquely_named = uniquely_named, allow_rename = allow_rename, 
 .     allow_empty = allow_empty, allow_predicates = allow_predicates, 
 .     type = type, error_call = error_call)
10. walk_data_tree(expr, data_mask, context_mask)
11. eval_c(expr, data_mask, context_mask)
12. reduce_sels(node, data_mask, context_mask, init = init)
13. walk_data_tree(new, data_mask, context_mask)
14. eval_c(expr, data_mask, context_mask)
15. reduce_sels(node, data_mask, context_mask, init = init)
16. walk_data_tree(new, data_mask, context_mask)
17. as_indices_sel_impl(out, vars = vars, strict = strict, data = data, 
  .     allow_predicates = allow_predicates, call = error_call, arg = as_label(expr))
18. as_indices_impl(x, vars, call = call, arg = arg, strict = strict)
19. chr_as_locations(x, vars, call = call, arg = arg)
20. vctrs::vec_as_location(x, n = length(vars), names = vars, call = call, 
  .     arg = arg)
21. (function () 
  . stop_subscript_oob(i = i, subscript_type = subscript_type, names = names, 
  .     subscript_action = subscript_action, subscript_arg = subscript_arg, 
  .     call = call))()
22. stop_subscript_oob(i = i, subscript_type = subscript_type, names = names, 
  .     subscript_action = subscript_action, subscript_arg = subscript_arg, 
  .     call = call)
23. stop_subscript(class = "vctrs_error_subscript_oob", i = i, subscript_type = subscript_type, 
  .     ..., call = call)
24. abort(class = c(class, "vctrs_error_subscript"), i = i, ..., 
  .     call = call)
25. signal_abort(cnd, .file)
26. signalCondition(cnd)
27. (function (cnd) 
  . {
  .     {
  .         .__handler_frame__. <- TRUE
  .         .__setup_frame__. <- frame
  .         if (inherits(cnd, "message")) {
  .             except <- c("warning", "error")
  .         }
  .         else if (inherits(cnd, "warning")) {
  .             except <- "error"
  .         }
  .         else {
  .             except <- ""
  .         }
  .     }
  .     while (!is_null(cnd)) {
  .         if (inherits(cnd, "vctrs_error_subscript")) {
  .             out <- handlers[[1L]](cnd)
  .             if (!inherits(out, "rlang_zap")) 
  .                 throw(out)
  .         }
  .         inherit <- .subset2(.subset2(cnd, "rlang"), "inherit")
  .         if (is_false(inherit)) {
  .             return()
  .         }
  .         cnd <- .subset2(cnd, "parent")
  .     }
  . })(structure(list(message = "", trace = structure(list(call = list(
  .     IRkernel::main(), kernel$run(), handle_shell(), executor$execute(msg), 
  .     tryCatch(evaluate(request$content$code, envir = .GlobalEnv, 
  .         output_handler = oh, stop_on_error = 1L), interrupt = function(cond) {
  .         log_debug("Interrupt during execution")
  .         interrupted <<- TRUE
  .     }, error = .self$handle_error), tryCatchList(expr, classes, 
  .         parentenv, handlers), tryCatchOne(tryCatchList(expr, 
  .         names[-nh], parentenv, handlers[-nh]), names[nh], parentenv, 
  .         handlers[[nh]]), doTryCatch(return(expr), name, parentenv, 
  .         handler), tryCatchList(expr, names[-nh], parentenv, handlers[-nh]), 
  .     tryCatchOne(expr, names, parentenv, handlers[[1L]]), doTryCatch(return(expr), 
  .         name, parentenv, handler), evaluate(request$content$code, 
  .         envir = .GlobalEnv, output_handler = oh, stop_on_error = 1L), 
  .     evaluate_call(expr, parsed$src[[i]], envir = envir, enclos = enclos, 
  .         debug = debug, last = i == length(out), use_try = stop_on_error != 
  .             2L, keep_warning = keep_warning, keep_message = keep_message, 
  .         log_echo = log_echo, log_warning = log_warning, output_handler = output_handler, 
  .         include_timing = include_timing), timing_fn(handle(ev <- withCallingHandlers(withVisible(eval_with_user_handlers(expr, 
  .         envir, enclos, user_handlers)), warning = wHandler, error = eHandler, 
  .         message = mHandler))), handle(ev <- withCallingHandlers(withVisible(eval_with_user_handlers(expr, 
  .         envir, enclos, user_handlers)), warning = wHandler, error = eHandler, 
  .         message = mHandler)), try(f, silent = TRUE), tryCatch(expr, 
  .         error = function(e) {
  .             call <- conditionCall(e)
  .             if (!is.null(call)) {
  .                 if (identical(call[[1L]], quote(doTryCatch))) 
  .                   call <- sys.call(-4L)
  .                 dcall <- deparse(call, nlines = 1L)
  .                 prefix <- paste("Error in", dcall, ": ")
  .                 LONG <- 75L
  .                 sm <- strsplit(conditionMessage(e), "\n")[[1L]]
  .                 w <- 14L + nchar(dcall, type = "w") + nchar(sm[1L], 
  .                   type = "w")
  .                 if (is.na(w)) 
  .                   w <- 14L + nchar(dcall, type = "b") + nchar(sm[1L], 
  .                     type = "b")
  .                 if (w > LONG) 
  .                   prefix <- paste0(prefix, "\n  ")
  .             }
  .             else prefix <- "Error : "
  .             msg <- paste0(prefix, conditionMessage(e), "\n")
  .             .Internal(seterrmessage(msg[1L]))
  .             if (!silent && isTRUE(getOption("show.error.messages"))) {
  .                 cat(msg, file = outFile)
  .                 .Internal(printDeferredWarnings())
  .             }
  .             invisible(structure(msg, class = "try-error", condition = e))
  .         }), tryCatchList(expr, classes, parentenv, handlers), 
  .     tryCatchOne(expr, names, parentenv, handlers[[1L]]), doTryCatch(return(expr), 
  .         name, parentenv, handler), withCallingHandlers(withVisible(eval_with_user_handlers(expr, 
  .         envir, enclos, user_handlers)), warning = wHandler, error = eHandler, 
  .         message = mHandler), withVisible(eval_with_user_handlers(expr, 
  .         envir, enclos, user_handlers)), eval_with_user_handlers(expr, 
  .         envir, enclos, user_handlers), eval(expr, envir, enclos), 
  .     eval(expr, envir, enclos), CCLE_exp %>% dplyr::select(c("Description", 
  .         select_cl)), dplyr::select(., c("Description", select_cl)), 
  .     select.data.frame(., c("Description", select_cl)), tidyselect::eval_select(expr(c(...)), 
  .         data = .data, error_call = error_call), eval_select_impl(data, 
  .         names(data), as_quosure(expr, env), include = include, 
  .         exclude = exclude, strict = strict, name_spec = name_spec, 
  .         allow_rename = allow_rename, allow_empty = allow_empty, 
  .         allow_predicates = allow_predicates, error_call = error_call, 
  .         ), with_subscript_errors(out <- vars_select_eval(vars, 
  .         expr, strict = strict, data = x, name_spec = name_spec, 
  .         uniquely_named = uniquely_named, allow_rename = allow_rename, 
  .         allow_empty = allow_empty, allow_predicates = allow_predicates, 
  .         type = type, error_call = error_call), type = type), 
  .     try_fetch(expr, vctrs_error_subscript = function(cnd) {
  .         cnd$subscript_action <- subscript_action(type)
  .         cnd$subscript_elt <- "column"
  .         cnd_signal(cnd)
  .     }), withCallingHandlers(expr, condition = function(cnd) {
  .         {
  .             .__handler_frame__. <- TRUE
  .             .__setup_frame__. <- frame
  .             if (inherits(cnd, "message")) {
  .                 except <- c("warning", "error")
  .             }
  .             else if (inherits(cnd, "warning")) {
  .                 except <- "error"
  .             }
  .             else {
  .                 except <- ""
  .             }
  .         }
  .         while (!is_null(cnd)) {
  .             if (inherits(cnd, "vctrs_error_subscript")) {
  .                 out <- handlers[[1L]](cnd)
  .                 if (!inherits(out, "rlang_zap")) 
  .                   throw(out)
  .             }
  .             inherit <- .subset2(.subset2(cnd, "rlang"), "inherit")
  .             if (is_false(inherit)) {
  .                 return()
  .             }
  .             cnd <- .subset2(cnd, "parent")
  .         }
  .     }), vars_select_eval(vars, expr, strict = strict, data = x, 
  .         name_spec = name_spec, uniquely_named = uniquely_named, 
  .         allow_rename = allow_rename, allow_empty = allow_empty, 
  .         allow_predicates = allow_predicates, type = type, error_call = error_call), 
  .     walk_data_tree(expr, data_mask, context_mask), eval_c(expr, 
  .         data_mask, context_mask), reduce_sels(node, data_mask, 
  .         context_mask, init = init), walk_data_tree(new, data_mask, 
  .         context_mask), eval_c(expr, data_mask, context_mask), 
  .     reduce_sels(node, data_mask, context_mask, init = init), 
  .     walk_data_tree(new, data_mask, context_mask), as_indices_sel_impl(out, 
  .         vars = vars, strict = strict, data = data, allow_predicates = allow_predicates, 
  .         call = error_call, arg = as_label(expr)), as_indices_impl(x, 
  .         vars, call = call, arg = arg, strict = strict), chr_as_locations(x, 
  .         vars, call = call, arg = arg), vctrs::vec_as_location(x, 
  .         n = length(vars), names = vars, call = call, arg = arg), 
  .     `<fn>`(), stop_subscript_oob(i = i, subscript_type = subscript_type, 
  .         names = names, subscript_action = subscript_action, subscript_arg = subscript_arg, 
  .         call = call), stop_subscript(class = "vctrs_error_subscript_oob", 
  .         i = i, subscript_type = subscript_type, ..., call = call), 
  .     abort(class = c(class, "vctrs_error_subscript"), i = i, ..., 
  .         call = call)), parent = c(0L, 1L, 2L, 3L, 4L, 5L, 6L, 
  . 7L, 6L, 9L, 10L, 4L, 12L, 13L, 13L, 15L, 16L, 17L, 18L, 19L, 
  . 13L, 13L, 13L, 23L, 24L, 0L, 0L, 0L, 28L, 29L, 30L, 31L, 32L, 
  . 30L, 34L, 35L, 36L, 37L, 38L, 39L, 40L, 41L, 42L, 43L, 44L, 0L, 
  . 46L, 47L, 48L), visible = c(TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, 
  . TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, 
  . TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, 
  . FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, 
  . FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, 
  . FALSE, FALSE, FALSE), namespace = c("IRkernel", NA, "IRkernel", 
  . NA, "base", "base", "base", "base", "base", "base", "base", "evaluate", 
  . "evaluate", "evaluate", "evaluate", "base", "base", "base", "base", 
  . "base", "base", "base", "evaluate", "base", "base", NA, "dplyr", 
  . "dplyr", "tidyselect", "tidyselect", "tidyselect", "rlang", "base", 
  . "tidyselect", "tidyselect", "tidyselect", "tidyselect", "tidyselect", 
  . "tidyselect", "tidyselect", "tidyselect", "tidyselect", "tidyselect", 
  . "tidyselect", "vctrs", "vctrs", "vctrs", "vctrs", "rlang"), scope = c("::", 
  . NA, "local", NA, "::", "local", "local", "local", "local", "local", 
  . "local", "::", ":::", "local", "local", "::", "::", "local", 
  . "local", "local", "::", "::", ":::", "::", "::", NA, "::", ":::", 
  . "::", ":::", ":::", "::", "::", ":::", ":::", ":::", ":::", ":::", 
  . ":::", ":::", ":::", ":::", ":::", ":::", "::", "local", ":::", 
  . ":::", "::"), error_frame = c(FALSE, FALSE, FALSE, FALSE, FALSE, 
  . FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, 
  . FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, 
  . FALSE, FALSE, FALSE, FALSE, TRUE, FALSE, FALSE, FALSE, FALSE, 
  . FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, 
  . FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE)), row.names = c(NA, 
  . -49L), version = 2L, class = c("rlang_trace", "rlib_trace", "tbl", 
  . "data.frame")), parent = NULL, i = c("1321N1_CENTRAL_NERVOUS_SYSTEM", 
  . "22RV1_PROSTATE", "42MGBA_CENTRAL_NERVOUS_SYSTEM", "5637_URINARY_TRACT", 
  . "639V_URINARY_TRACT", "697_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "769P_KIDNEY", "786O_KIDNEY", "8305C_THYROID", "8505C_THYROID", 
  . "8MGBA_CENTRAL_NERVOUS_SYSTEM", "A172_CENTRAL_NERVOUS_SYSTEM", 
  . "A204_SOFT_TISSUE", "A2058_SKIN", "A253_SALIVARY_GLAND", "A2780_OVARY", 
  . "A375_SKIN", "A549_LUNG", "A673_BONE", "ACHN_KIDNEY", "ALLSIL_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "AMO1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "AN3CA_ENDOMETRIUM", 
  . "ASPC1_PANCREAS", "AU565_BREAST", "AZ521_STOMACH", "BCPAP_THYROID", 
  . "BDCM_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "BFTC909_KIDNEY", 
  . "BGC823_STOMACH", "BL41_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "BL70_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "BT20_BREAST", "BT474_BREAST", 
  . "BT549_BREAST", "BXPC3_PANCREAS", "C2BBE1_LARGE_INTESTINE", "C32_SKIN", 
  . "C3A_LIVER", "CAKI2_KIDNEY", "CAL12T_LUNG", "CAL27_UPPER_AERODIGESTIVE_TRACT", 
  . "CAL78_BONE", "CAL851_BREAST", "CALU1_LUNG", "CALU3_LUNG", "CALU6_LUNG", 
  . "CAMA1_BREAST", "CAPAN2_PANCREAS", "CAS1_CENTRAL_NERVOUS_SYSTEM", 
  . "CCK81_LARGE_INTESTINE", "CHL1_SKIN", "CHP212_AUTONOMIC_GANGLIA", 
  . "CI1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "CMK86_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "COLO201_LARGE_INTESTINE", "COLO205_LARGE_INTESTINE", "COLO320_LARGE_INTESTINE", 
  . "COLO677_LUNG", "COLO678_LARGE_INTESTINE", "COLO679_SKIN", "COLO699_LUNG", 
  . "COLO741_SKIN", "CORL105_LUNG", "CORL23_LUNG", "COV318_OVARY", 
  . "COV504_OVARY", "DAOY_CENTRAL_NERVOUS_SYSTEM", "DBTRG05MG_CENTRAL_NERVOUS_SYSTEM", 
  . "DEL_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "DETROIT562_UPPER_AERODIGESTIVE_TRACT", 
  . "DKMG_CENTRAL_NERVOUS_SYSTEM", "DMS114_LUNG", "DOHH2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "DOV13_OVARY", "DU145_PROSTATE", "DV90_LUNG", "EB1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "EB2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "EBC1_LUNG", "EFE184_ENDOMETRIUM", 
  . "EFM19_BREAST", "EFO21_OVARY", "EFO27_OVARY", "EM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "EN_ENDOMETRIUM", "ES2_OVARY", "ESS1_ENDOMETRIUM", "F36P_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "FADU_UPPER_AERODIGESTIVE_TRACT", "FU97_STOMACH", "FUOV1_OVARY", 
  . "G361_SKIN", "G401_SOFT_TISSUE", "G402_SOFT_TISSUE", "GAMG_CENTRAL_NERVOUS_SYSTEM", 
  . "GB1_CENTRAL_NERVOUS_SYSTEM", "GCIY_STOMACH", "GCT_SOFT_TISSUE", 
  . "GI1_CENTRAL_NERVOUS_SYSTEM", "GLC82_LUNG", "GMS10_CENTRAL_NERVOUS_SYSTEM", 
  . "GRANTA519_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "H4_CENTRAL_NERVOUS_SYSTEM", 
  . "HARA_LUNG", "HCC1187_BREAST", "HCC1395_BREAST", "HCC15_LUNG", 
  . "HCC1569_BREAST", "HCC1806_BREAST", "HCC1954_BREAST", "HCC2935_LUNG", 
  . "HCC4006_LUNG", "HCC44_LUNG", "HCC56_LARGE_INTESTINE", "HCC70_BREAST", 
  . "HCC78_LUNG", "HCC827_LUNG", "HCT116_LARGE_INTESTINE", "HCT15_LARGE_INTESTINE", 
  . "HDMYZ_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HDQP1_BREAST", "HEC151_ENDOMETRIUM", 
  . "HEC1A_ENDOMETRIUM", "HEC1B_ENDOMETRIUM", "HEC251_ENDOMETRIUM", 
  . "HEC265_ENDOMETRIUM", "HEC59_ENDOMETRIUM", "HEC6_ENDOMETRIUM", 
  . "HEL9217_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HEP3B217_LIVER", 
  . "HEPG2_LIVER", "HEYA8_OVARY", "HGC27_STOMACH", "HH_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "HLE_LIVER", "HLF_LIVER", "HMC18_BREAST", "HMCB_SKIN", "HOS_BONE", 
  . "HPAC_PANCREAS", "HPAFII_PANCREAS", "HS229T_LUNG", "HS294T_SKIN", 
  . "HS578T_BREAST", "HS683_CENTRAL_NERVOUS_SYSTEM", "HS695T_SKIN", 
  . "HS729_SOFT_TISSUE", "HS739T_BREAST", "HS746T_STOMACH", "HS766T_PANCREAS", 
  . "HS840T_UPPER_AERODIGESTIVE_TRACT", "HS852T_SKIN", "HS895T_SKIN", 
  . "HS936T_SKIN", "HS939T_SKIN", "HS944T_SKIN", "HSC2_UPPER_AERODIGESTIVE_TRACT", 
  . "HT_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HT1080_SOFT_TISSUE", 
  . "HT1197_URINARY_TRACT", "HT1376_URINARY_TRACT", "HT144_SKIN", 
  . "HT29_LARGE_INTESTINE", "HUCCT1_BILIARY_TRACT", "HUH1_LIVER", 
  . "HUPT3_PANCREAS", "HUPT4_PANCREAS", "HUT78_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "IALM_LUNG", "IGR37_SKIN", "IGR39_SKIN", "IGROV1_OVARY", "IM95_STOMACH", 
  . "IMR32_AUTONOMIC_GANGLIA", "IPC298_SKIN", "ISHIKAWAHERAKLIO02ER_ENDOMETRIUM", 
  . "ISTMES1_PLEURA", "ISTMES2_PLEURA", "J82_URINARY_TRACT", "JHH2_LIVER", 
  . "JHH4_LIVER", "JHH5_LIVER", "JHH6_LIVER", "JHH7_LIVER", "JHOS2_OVARY", 
  . "JHOS4_OVARY", "JHUEM2_ENDOMETRIUM", "JM1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "JMSU1_URINARY_TRACT", "JURKAT_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "JVM3_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "K029AX_SKIN", "KALS1_CENTRAL_NERVOUS_SYSTEM", 
  . "KARPAS299_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KARPAS422_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KARPAS620_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KASUMI2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KCIMOH1_PANCREAS", "KCL22_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KE39_STOMACH", "KE97_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KELLY_AUTONOMIC_GANGLIA", 
  . "KG1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KHM1B_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KLE_ENDOMETRIUM", "KMBC2_URINARY_TRACT", "KMM1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KMRC1_KIDNEY", "KMRC2_KIDNEY", "KMS11_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KMS12BM_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KMS26_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KMS34_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KNS42_CENTRAL_NERVOUS_SYSTEM", 
  . "KNS60_CENTRAL_NERVOUS_SYSTEM", "KNS62_LUNG", "KNS81_CENTRAL_NERVOUS_SYSTEM", 
  . "KO52_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KP1N_PANCREAS", "KP1NL_PANCREAS", 
  . "KP2_PANCREAS", "KP3_PANCREAS", "KP4_PANCREAS", "KPNSI9S_AUTONOMIC_GANGLIA", 
  . "KU812_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KURAMOCHI_OVARY", 
  . "KYM1_SOFT_TISSUE", "KYSE140_OESOPHAGUS", "KYSE150_OESOPHAGUS", 
  . "KYSE180_OESOPHAGUS", "KYSE30_OESOPHAGUS", "KYSE410_OESOPHAGUS", 
  . "KYSE450_OESOPHAGUS", "KYSE510_OESOPHAGUS", "KYSE520_OESOPHAGUS", 
  . "KYSE70_OESOPHAGUS", "L33_PANCREAS", "L363_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "L428_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "LC1SQSF_LUNG", "LCLC103H_LUNG", 
  . "LN18_CENTRAL_NERVOUS_SYSTEM", "LN229_CENTRAL_NERVOUS_SYSTEM", 
  . "LOUNH91_LUNG", "LOXIMVI_SKIN", "LP1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "LS123_LARGE_INTESTINE", "LS411N_LARGE_INTESTINE", "LS513_LARGE_INTESTINE", 
  . "LU99_LUNG", "LUDLU1_LUNG", "M059J", "MALME3M_SKIN", "MB157_BREAST", 
  . "MC116_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MCAS_OVARY", "MCF7_BREAST", 
  . "MDAMB157_BREAST", "MDAMB175VII_BREAST", "MDAMB415_BREAST", "MDAMB435S_SKIN", 
  . "MDAMB436_BREAST", "MDAMB453_BREAST", "MDAMB468_BREAST", "MEC1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "MEG01_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MELHO_SKIN", "MESSA_SOFT_TISSUE", 
  . "MEWO_SKIN", "MFE280_ENDOMETRIUM", "MFE296_ENDOMETRIUM", "MFE319_ENDOMETRIUM", 
  . "MG63_BONE", "MHHES1_BONE", "MIAPACA2_PANCREAS", "MINO_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "MJ_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MKN45_STOMACH", "MKN7_STOMACH", 
  . "MKN74_STOMACH", "MOGGCCM_CENTRAL_NERVOUS_SYSTEM", "MOLP8_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "MOLT16_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MONOMAC1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "MORCPR_LUNG", "MPP89_PLEURA", "MSTO211H_PLEURA", "NCIH1048_LUNG", 
  . "NCIH1092_LUNG", "NCIH1155_LUNG", "NCIH1184_LUNG", "NCIH1299_LUNG", 
  . "NCIH1339_LUNG", "NCIH1341_LUNG", "NCIH1355_LUNG", "NCIH1373_LUNG", 
  . "NCIH1563_LUNG", "NCIH1568_LUNG", "NCIH1573_LUNG", "NCIH1581_LUNG", 
  . "NCIH1648_LUNG", "NCIH1650_LUNG", "NCIH1651_LUNG", "NCIH1666_LUNG", 
  . "NCIH1693_LUNG", "NCIH1694_LUNG", "NCIH1703_LUNG", "NCIH1792_LUNG", 
  . "NCIH1793_LUNG", "NCIH1869_LUNG", "NCIH1915_LUNG", "NCIH1944_LUNG", 
  . "NCIH1975_LUNG", "NCIH2009_LUNG", "NCIH2023_LUNG", "NCIH2030_LUNG", 
  . "NCIH2052_PLEURA", "NCIH2085_LUNG", "NCIH2087_LUNG", "NCIH211_LUNG", 
  . "NCIH2122_LUNG", "NCIH2170_LUNG", "NCIH2172_LUNG", "NCIH2228_LUNG", 
  . "NCIH226_LUNG", "NCIH2286_LUNG", "NCIH23_LUNG", "NCIH2444_LUNG", 
  . "NCIH2452_PLEURA", "NCIH28_PLEURA", "NCIH322_LUNG", "NCIH3255_LUNG", 
  . "NCIH358_LUNG", "NCIH441_LUNG", "NCIH460_LUNG", "NCIH520_LUNG", 
  . "NCIH522_LUNG", "NCIH647_LUNG", "NCIH650_LUNG", "NCIH661_LUNG", 
  . "NCIH727_LUNG", "NCIH747_LARGE_INTESTINE", "NCIH810_LUNG", "NCIN87_STOMACH", 
  . "NCO2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "NIHOVCAR3_OVARY", 
  . "NUGC3_STOMACH", "NUGC4_STOMACH", "OC314_OVARY", "OC315_OVARY", 
  . "OC316_OVARY", "OCIAML2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "OCIAML5_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "OCILY10_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "OCUM1_STOMACH", "OE21_OESOPHAGUS", "OE33_OESOPHAGUS", "ONCODG1_OVARY", 
  . "ONS76_CENTRAL_NERVOUS_SYSTEM", "OPM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "OV90_OVARY", "OVCAR4_OVARY", "OVCAR8_OVARY", "OVMANA_OVARY", 
  . "OVSAHO_OVARY", "OVTOKO_OVARY", "P12ICHIKAWA_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "P31FUJ_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "P3HR1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "PANC0203_PANCREAS", "PANC0327_PANCREAS", "PANC0403_PANCREAS", 
  . "PANC1005_PANCREAS", "PATU8902_PANCREAS", "PC14_LUNG", "PC3_PROSTATE", 
  . "PFEIFFER_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "PK1_PANCREAS", 
  . "PK45H_PANCREAS", "PK59_PANCREAS", "PL45_PANCREAS", "PLCPRF5_LIVER", 
  . "PSN1_PANCREAS", "QGP1_PANCREAS", "RAJI_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "RD_SOFT_TISSUE", "REH_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "RERFGC1B_STOMACH", 
  . "RERFLCAI_LUNG", "RERFLCMS_LUNG", "RKN_OVARY", "RKO_LARGE_INTESTINE", 
  . "RL952_ENDOMETRIUM", "RPMI7951_SKIN", "RPMI8402_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "RT112_URINARY_TRACT", "RT4_URINARY_TRACT", "RVH421_SKIN", "SAOS2_BONE", 
  . "SBC5_LUNG", "SCABER_URINARY_TRACT", "SCC25_UPPER_AERODIGESTIVE_TRACT", 
  . "SCC9_UPPER_AERODIGESTIVE_TRACT", "SF126_CENTRAL_NERVOUS_SYSTEM", 
  . "SF295_CENTRAL_NERVOUS_SYSTEM", "SF8657", "SH10TC_STOMACH", "SHP77_LUNG", 
  . "SIGM5_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SIMA_AUTONOMIC_GANGLIA", 
  . "SJRH30_SOFT_TISSUE", "SJSA1_BONE", "SKBR3_BREAST", "SKCO1_LARGE_INTESTINE", 
  . "SKES1_BONE", "SKHEP1_LIVER", "SKLMS1_SOFT_TISSUE", "SKLU1_LUNG", 
  . "SKMEL2_SKIN", "SKMEL24_SKIN", "SKMEL30_SKIN", "SKMEL31_SKIN", 
  . "SKMEL5_SKIN", "SKMES1_LUNG", "SKMM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "SKNAS_AUTONOMIC_GANGLIA", "SKNBE2_AUTONOMIC_GANGLIA", "SKNDZ_AUTONOMIC_GANGLIA", 
  . "SKNFI_AUTONOMIC_GANGLIA", "SKNSH_AUTONOMIC_GANGLIA", "SKOV3_OVARY", 
  . "SNGM_ENDOMETRIUM", "SNU1_STOMACH", "SNU16_STOMACH", "SNU182_LIVER", 
  . "SNU387_LIVER", "SNU398_LIVER", "SNU423_LIVER", "SNU449_LIVER", 
  . "SNU475_LIVER", "SNUC2A_LARGE_INTESTINE", "SNUC2B", "SQ1_LUNG", 
  . "SU8686_PANCREAS", "SUDHL10_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "SUDHL4_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SUDHL6_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "SUDHL8_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SUIT2_PANCREAS", 
  . "SUPM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SUPT1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "SW1088_CENTRAL_NERVOUS_SYSTEM", "SW1271_LUNG", "SW1353_BONE", 
  . "SW1417_LARGE_INTESTINE", "SW1573_LUNG", "SW1990_PANCREAS", "SW403_LARGE_INTESTINE", 
  . "SW48_LARGE_INTESTINE", "SW480_LARGE_INTESTINE", "SW579_THYROID", 
  . "SW620_LARGE_INTESTINE", "SW780_URINARY_TRACT", "SW900_LUNG", 
  . "T24_URINARY_TRACT", "T3M10_LUNG", "T47D_BREAST", "T84_LARGE_INTESTINE", 
  . "T98G_CENTRAL_NERVOUS_SYSTEM", "TC71_BONE", "TCCSUP_URINARY_TRACT", 
  . "TE1_OESOPHAGUS", "TE11_OESOPHAGUS", "TE15_OESOPHAGUS", "TE5_OESOPHAGUS", 
  . "TE617T_SOFT_TISSUE", "TE9_OESOPHAGUS", "TEN_ENDOMETRIUM", "TOLEDO_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "TOV112D_OVARY", "TOV21G_OVARY", "TT2609C02_THYROID", "TYKNU_OVARY", 
  . "U118MG_CENTRAL_NERVOUS_SYSTEM", "U2OS_BONE", "U87MG_CENTRAL_NERVOUS_SYSTEM", 
  . "U937_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "UACC257_SKIN", "UACC62_SKIN", 
  . "UACC812_BREAST", "UMUC3_URINARY_TRACT", "VMRCLCD_LUNG", "VMRCRCW_KIDNEY", 
  . "VMRCRCZ_KIDNEY", "WM115_SKIN", "WM1799_SKIN", "WM2664_SKIN", 
  . "WM793_SKIN", "WM88_SKIN", "WM983B_SKIN", "YKG1_CENTRAL_NERVOUS_SYSTEM", 
  . "ZR751_BREAST", "ZR7530_BREAST", "1321N1_CENTRAL_NERVOUS_SYSTEM", 
  . "22RV1_PROSTATE", "42MGBA_CENTRAL_NERVOUS_SYSTEM", "5637_URINARY_TRACT", 
  . "639V_URINARY_TRACT", "697_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "769P_KIDNEY", "8305C_THYROID", "8505C_THYROID", "8MGBA_CENTRAL_NERVOUS_SYSTEM", 
  . "A172_CENTRAL_NERVOUS_SYSTEM", "A204_SOFT_TISSUE", "A2058_SKIN", 
  . "A253_SALIVARY_GLAND", "A2780_OVARY", "A375_SKIN", "A549_LUNG", 
  . "A673_BONE", "ACHN_KIDNEY", "ALLSIL_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "AMO1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "AN3CA_ENDOMETRIUM", 
  . "ASPC1_PANCREAS", "AU565_BREAST", "AZ521_STOMACH", "BCPAP_THYROID", 
  . "BDCM_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "BFTC909_KIDNEY", 
  . "BGC823_STOMACH", "BL41_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "BL70_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "BT20_BREAST", "BT474_BREAST", 
  . "BT549_BREAST", "BXPC3_PANCREAS", "C2BBE1_LARGE_INTESTINE", "C32_SKIN", 
  . "C3A_LIVER", "CAKI2_KIDNEY", "CAL12T_LUNG", "CAL27_UPPER_AERODIGESTIVE_TRACT", 
  . "CAL78_BONE", "CAL851_BREAST", "CALU1_LUNG", "CALU3_LUNG", "CALU6_LUNG", 
  . "CAMA1_BREAST", "CAPAN2_PANCREAS", "CAS1_CENTRAL_NERVOUS_SYSTEM", 
  . "CCK81_LARGE_INTESTINE", "CHL1_SKIN", "CHP212_AUTONOMIC_GANGLIA", 
  . "CI1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "CMK86_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "COLO201_LARGE_INTESTINE", "COLO205_LARGE_INTESTINE", "COLO320_LARGE_INTESTINE", 
  . "COLO677_LUNG", "COLO678_LARGE_INTESTINE", "COLO679_SKIN", "COLO699_LUNG", 
  . "COLO741_SKIN", "CORL105_LUNG", "CORL23_LUNG", "COV318_OVARY", 
  . "COV504_OVARY", "DAOY_CENTRAL_NERVOUS_SYSTEM", "DBTRG05MG_CENTRAL_NERVOUS_SYSTEM", 
  . "DEL_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "DETROIT562_UPPER_AERODIGESTIVE_TRACT", 
  . "DKMG_CENTRAL_NERVOUS_SYSTEM", "DMS114_LUNG", "DOHH2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "DOV13_OVARY", "DU145_PROSTATE", "DV90_LUNG", "EB1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "EB2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "EBC1_LUNG", "EFE184_ENDOMETRIUM", 
  . "EFM19_BREAST", "EFO21_OVARY", "EM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "EN_ENDOMETRIUM", "ES2_OVARY", "ESS1_ENDOMETRIUM", "F36P_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "FADU_UPPER_AERODIGESTIVE_TRACT", "FU97_STOMACH", "FUOV1_OVARY", 
  . "G361_SKIN", "G401_SOFT_TISSUE", "G402_SOFT_TISSUE", "GAMG_CENTRAL_NERVOUS_SYSTEM", 
  . "GB1_CENTRAL_NERVOUS_SYSTEM", "GCIY_STOMACH", "GCT_SOFT_TISSUE", 
  . "GI1_CENTRAL_NERVOUS_SYSTEM", "GLC82_LUNG", "GMS10_CENTRAL_NERVOUS_SYSTEM", 
  . "GRANTA519_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "H4_CENTRAL_NERVOUS_SYSTEM", 
  . "HARA_LUNG", "HCC1187_BREAST", "HCC1395_BREAST", "HCC15_LUNG", 
  . "HCC1569_BREAST", "HCC1806_BREAST", "HCC1954_BREAST", "HCC2935_LUNG", 
  . "HCC4006_LUNG", "HCC44_LUNG", "HCC56_LARGE_INTESTINE", "HCC70_BREAST", 
  . "HCC78_LUNG", "HCC827_LUNG", "HCT116_LARGE_INTESTINE", "HCT15_LARGE_INTESTINE", 
  . "HDMYZ_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HDQP1_BREAST", "HEC151_ENDOMETRIUM", 
  . "HEC1A_ENDOMETRIUM", "HEC1B_ENDOMETRIUM", "HEC251_ENDOMETRIUM", 
  . "HEC265_ENDOMETRIUM", "HEC59_ENDOMETRIUM", "HEC6_ENDOMETRIUM", 
  . "HEL9217_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HEP3B217_LIVER", 
  . "HEPG2_LIVER", "HGC27_STOMACH", "HH_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "HLE_LIVER", "HLF_LIVER", "HMC18_BREAST", "HMCB_SKIN", "HOS_BONE", 
  . "HPAC_PANCREAS", "HPAFII_PANCREAS", "HS229T_LUNG", "HS294T_SKIN", 
  . "HS578T_BREAST", "HS683_CENTRAL_NERVOUS_SYSTEM", "HS695T_SKIN", 
  . "HS729_SOFT_TISSUE", "HS739T_BREAST", "HS746T_STOMACH", "HS766T_PANCREAS", 
  . "HS840T_UPPER_AERODIGESTIVE_TRACT", "HS852T_SKIN", "HS895T_SKIN", 
  . "HS936T_SKIN", "HS939T_SKIN", "HS944T_SKIN", "HSC2_UPPER_AERODIGESTIVE_TRACT", 
  . "HT_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HT1080_SOFT_TISSUE", 
  . "HT1197_URINARY_TRACT", "HT1376_URINARY_TRACT", "HT144_SKIN", 
  . "HT29_LARGE_INTESTINE", "HUCCT1_BILIARY_TRACT", "HUH1_LIVER", 
  . "HUPT3_PANCREAS", "HUPT4_PANCREAS", "HUT78_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "IALM_LUNG", "IGR37_SKIN", "IGR39_SKIN", "IM95_STOMACH", "IMR32_AUTONOMIC_GANGLIA", 
  . "IPC298_SKIN", "ISHIKAWAHERAKLIO02ER_ENDOMETRIUM", "ISTMES1_PLEURA", 
  . "ISTMES2_PLEURA", "J82_URINARY_TRACT", "JHH2_LIVER", "JHH4_LIVER", 
  . "JHH5_LIVER", "JHH6_LIVER", "JHH7_LIVER", "JHOS2_OVARY", "JHOS4_OVARY", 
  . "JHUEM2_ENDOMETRIUM", "JM1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "JMSU1_URINARY_TRACT", "JURKAT_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "JVM3_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "K029AX_SKIN", "KALS1_CENTRAL_NERVOUS_SYSTEM", 
  . "KARPAS299_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KARPAS422_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KARPAS620_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KASUMI2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KCIMOH1_PANCREAS", "KCL22_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KE39_STOMACH", "KE97_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KELLY_AUTONOMIC_GANGLIA", 
  . "KG1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KHM1B_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KLE_ENDOMETRIUM", "KMBC2_URINARY_TRACT", "KMM1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KMRC1_KIDNEY", "KMRC2_KIDNEY", "KMS11_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KMS12BM_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KMS26_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KMS34_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KNS42_CENTRAL_NERVOUS_SYSTEM", 
  . "KNS60_CENTRAL_NERVOUS_SYSTEM", "KNS62_LUNG", "KNS81_CENTRAL_NERVOUS_SYSTEM", 
  . "KO52_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KP1N_PANCREAS", "KP1NL_PANCREAS", 
  . "KP3_PANCREAS", "KP4_PANCREAS", "KPNSI9S_AUTONOMIC_GANGLIA", 
  . "KU812_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KURAMOCHI_OVARY", 
  . "KYM1_SOFT_TISSUE", "KYSE140_OESOPHAGUS", "KYSE150_OESOPHAGUS", 
  . "KYSE180_OESOPHAGUS", "KYSE30_OESOPHAGUS", "KYSE410_OESOPHAGUS", 
  . "KYSE450_OESOPHAGUS", "KYSE510_OESOPHAGUS", "KYSE520_OESOPHAGUS", 
  . "KYSE70_OESOPHAGUS", "L33_PANCREAS", "L363_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "L428_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "LC1SQSF_LUNG", "LCLC103H_LUNG", 
  . "LN229_CENTRAL_NERVOUS_SYSTEM", "LOUNH91_LUNG", "LOXIMVI_SKIN", 
  . "LP1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "LS123_LARGE_INTESTINE", 
  . "LS411N_LARGE_INTESTINE", "LS513_LARGE_INTESTINE", "LU99_LUNG", 
  . "LUDLU1_LUNG", "M059J", "MALME3M_SKIN", "MB157_BREAST", "MC116_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "MCAS_OVARY", "MCF7_BREAST", "MDAMB157_BREAST", "MDAMB175VII_BREAST", 
  . "MDAMB415_BREAST", "MDAMB435S_SKIN", "MDAMB436_BREAST", "MDAMB453_BREAST", 
  . "MDAMB468_BREAST", "MEC1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "MEG01_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MELHO_SKIN", "MESSA_SOFT_TISSUE", 
  . "MEWO_SKIN", "MFE280_ENDOMETRIUM", "MFE296_ENDOMETRIUM", "MFE319_ENDOMETRIUM", 
  . "MG63_BONE", "MHHES1_BONE", "MIAPACA2_PANCREAS", "MINO_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "MJ_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MKN45_STOMACH", "MKN7_STOMACH", 
  . "MKN74_STOMACH", "MOGGCCM_CENTRAL_NERVOUS_SYSTEM", "MOLP8_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "MOLT16_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MONOMAC1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "MORCPR_LUNG", "MPP89_PLEURA", "MSTO211H_PLEURA", "NCIH1048_LUNG", 
  . "NCIH1092_LUNG", "NCIH1155_LUNG", "NCIH1184_LUNG", "NCIH1299_LUNG", 
  . "NCIH1339_LUNG", "NCIH1341_LUNG", "NCIH1355_LUNG", "NCIH1373_LUNG", 
  . "NCIH1563_LUNG", "NCIH1568_LUNG", "NCIH1573_LUNG", "NCIH1581_LUNG", 
  . "NCIH1648_LUNG", "NCIH1650_LUNG", "NCIH1651_LUNG", "NCIH1666_LUNG", 
  . "NCIH1693_LUNG", "NCIH1694_LUNG", "NCIH1703_LUNG", "NCIH1792_LUNG", 
  . "NCIH1793_LUNG", "NCIH1869_LUNG", "NCIH1915_LUNG", "NCIH1944_LUNG", 
  . "NCIH1975_LUNG", "NCIH2009_LUNG", "NCIH2023_LUNG", "NCIH2030_LUNG", 
  . "NCIH2052_PLEURA", "NCIH2085_LUNG", "NCIH2087_LUNG", "NCIH211_LUNG", 
  . "NCIH2122_LUNG", "NCIH2170_LUNG", "NCIH2172_LUNG", "NCIH2228_LUNG", 
  . "NCIH226_LUNG", "NCIH2286_LUNG", "NCIH23_LUNG", "NCIH2444_LUNG", 
  . "NCIH2452_PLEURA", "NCIH28_PLEURA", "NCIH322_LUNG", "NCIH3255_LUNG", 
  . "NCIH358_LUNG", "NCIH441_LUNG", "NCIH460_LUNG", "NCIH520_LUNG", 
  . "NCIH522_LUNG", "NCIH647_LUNG", "NCIH650_LUNG", "NCIH661_LUNG", 
  . "NCIH727_LUNG", "NCIH747_LARGE_INTESTINE", "NCIH810_LUNG", "NCIN87_STOMACH", 
  . "NCO2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "NIHOVCAR3_OVARY", 
  . "NUGC3_STOMACH", "NUGC4_STOMACH", "OC314_OVARY", "OC315_OVARY", 
  . "OC316_OVARY", "OCIAML2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "OCIAML5_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "OCILY10_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "OCUM1_STOMACH", "OE21_OESOPHAGUS", "OE33_OESOPHAGUS", "ONCODG1_OVARY", 
  . "ONS76_CENTRAL_NERVOUS_SYSTEM", "OPM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "OV90_OVARY", "OVCAR4_OVARY", "OVCAR8_OVARY", "OVMANA_OVARY", 
  . "OVSAHO_OVARY", "P12ICHIKAWA_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "P31FUJ_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "P3HR1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "PANC0203_PANCREAS", "PANC0327_PANCREAS", "PANC0403_PANCREAS", 
  . "PANC1005_PANCREAS", "PATU8902_PANCREAS", "PC14_LUNG", "PC3_PROSTATE", 
  . "PFEIFFER_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "PK1_PANCREAS", 
  . "PK45H_PANCREAS", "PK59_PANCREAS", "PL45_PANCREAS", "PLCPRF5_LIVER", 
  . "PSN1_PANCREAS", "QGP1_PANCREAS", "RAJI_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "RD_SOFT_TISSUE", "REH_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "RERFGC1B_STOMACH", 
  . "RERFLCAI_LUNG", "RERFLCMS_LUNG", "RKN_OVARY", "RKO_LARGE_INTESTINE", 
  . "RL952_ENDOMETRIUM", "RPMI7951_SKIN", "RPMI8402_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "RT112_URINARY_TRACT", "RT4_URINARY_TRACT", "RVH421_SKIN", "SAOS2_BONE", 
  . "SBC5_LUNG", "SCABER_URINARY_TRACT", "SCC25_UPPER_AERODIGESTIVE_TRACT", 
  . "SCC9_UPPER_AERODIGESTIVE_TRACT", "SF126_CENTRAL_NERVOUS_SYSTEM", 
  . "SF295_CENTRAL_NERVOUS_SYSTEM", "SF8657", "SH10TC_STOMACH", "SHP77_LUNG", 
  . "SIGM5_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SIMA_AUTONOMIC_GANGLIA", 
  . "SJRH30_SOFT_TISSUE", "SJSA1_BONE", "SKBR3_BREAST", "SKCO1_LARGE_INTESTINE", 
  . "SKES1_BONE", "SKHEP1_LIVER", "SKLMS1_SOFT_TISSUE", "SKLU1_LUNG", 
  . "SKMEL2_SKIN", "SKMEL24_SKIN", "SKMEL30_SKIN", "SKMEL31_SKIN", 
  . "SKMEL5_SKIN", "SKMES1_LUNG", "SKMM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "SKNAS_AUTONOMIC_GANGLIA", "SKNBE2_AUTONOMIC_GANGLIA", "SKNDZ_AUTONOMIC_GANGLIA", 
  . "SKNFI_AUTONOMIC_GANGLIA", "SKNSH_AUTONOMIC_GANGLIA", "SKOV3_OVARY", 
  . "SNGM_ENDOMETRIUM", "SNU1_STOMACH", "SNU16_STOMACH", "SNU182_LIVER", 
  . "SNU387_LIVER", "SNU398_LIVER", "SNU423_LIVER", "SNU449_LIVER", 
  . "SNU475_LIVER", "SNUC2A_LARGE_INTESTINE", "SNUC2B", "SQ1_LUNG", 
  . "SU8686_PANCREAS", "SUDHL10_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "SUDHL4_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SUDHL6_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "SUDHL8_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SUIT2_PANCREAS", 
  . "SUPM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SUPT1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "SW1088_CENTRAL_NERVOUS_SYSTEM", "SW1271_LUNG", "SW1353_BONE", 
  . "SW1417_LARGE_INTESTINE", "SW1573_LUNG", "SW1990_PANCREAS", "SW403_LARGE_INTESTINE", 
  . "SW48_LARGE_INTESTINE", "SW480_LARGE_INTESTINE", "SW579_THYROID", 
  . "SW620_LARGE_INTESTINE", "SW780_URINARY_TRACT", "SW900_LUNG", 
  . "T24_URINARY_TRACT", "T3M10_LUNG", "T47D_BREAST", "T84_LARGE_INTESTINE", 
  . "T98G_CENTRAL_NERVOUS_SYSTEM", "TC71_BONE", "TCCSUP_URINARY_TRACT", 
  . "TE1_OESOPHAGUS", "TE15_OESOPHAGUS", "TE5_OESOPHAGUS", "TE617T_SOFT_TISSUE", 
  . "TE9_OESOPHAGUS", "TEN_ENDOMETRIUM", "TOLEDO_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "TOV112D_OVARY", "TOV21G_OVARY", "TT2609C02_THYROID", "TYKNU_OVARY", 
  . "U118MG_CENTRAL_NERVOUS_SYSTEM", "U2OS_BONE", "U87MG_CENTRAL_NERVOUS_SYSTEM", 
  . "U937_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "UACC257_SKIN", "UACC62_SKIN", 
  . "UACC812_BREAST", "UMUC3_URINARY_TRACT", "VMRCLCD_LUNG", "VMRCRCW_KIDNEY", 
  . "VMRCRCZ_KIDNEY", "WM115_SKIN", "WM1799_SKIN", "WM2664_SKIN", 
  . "WM793_SKIN", "WM88_SKIN", "WM983B_SKIN", "YKG1_CENTRAL_NERVOUS_SYSTEM", 
  . "ZR751_BREAST", "ZR7530_BREAST", "1321N1_CENTRAL_NERVOUS_SYSTEM", 
  . "22RV1_PROSTATE", "42MGBA_CENTRAL_NERVOUS_SYSTEM", "5637_URINARY_TRACT", 
  . "639V_URINARY_TRACT", "697_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "769P_KIDNEY", "786O_KIDNEY", "8305C_THYROID", "8505C_THYROID", 
  . "8MGBA_CENTRAL_NERVOUS_SYSTEM", "A172_CENTRAL_NERVOUS_SYSTEM", 
  . "A204_SOFT_TISSUE", "A2058_SKIN", "A253_SALIVARY_GLAND", "A2780_OVARY", 
  . "A375_SKIN", "A549_LUNG", "A673_BONE", "ACHN_KIDNEY", "ALLSIL_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "AMO1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "AN3CA_ENDOMETRIUM", 
  . "ASPC1_PANCREAS", "AU565_BREAST", "AZ521_STOMACH", "BCPAP_THYROID", 
  . "BDCM_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "BFTC909_KIDNEY", 
  . "BGC823_STOMACH", "BL41_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "BL70_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "BT20_BREAST", "BT474_BREAST", 
  . "BT549_BREAST", "BXPC3_PANCREAS", "C2BBE1_LARGE_INTESTINE", "C32_SKIN", 
  . "C3A_LIVER", "CAKI2_KIDNEY", "CAL12T_LUNG", "CAL27_UPPER_AERODIGESTIVE_TRACT", 
  . "CAL78_BONE", "CAL851_BREAST", "CALU1_LUNG", "CALU3_LUNG", "CALU6_LUNG", 
  . "CAMA1_BREAST", "CAPAN2_PANCREAS", "CAS1_CENTRAL_NERVOUS_SYSTEM", 
  . "CCK81_LARGE_INTESTINE", "CHL1_SKIN", "CHP212_AUTONOMIC_GANGLIA", 
  . "CI1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "CMK86_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "COLO201_LARGE_INTESTINE", "COLO205_LARGE_INTESTINE", "COLO320_LARGE_INTESTINE", 
  . "COLO677_LUNG", "COLO678_LARGE_INTESTINE", "COLO679_SKIN", "COLO699_LUNG", 
  . "COLO741_SKIN", "CORL105_LUNG", "CORL23_LUNG", "COV318_OVARY", 
  . "COV504_OVARY", "DAOY_CENTRAL_NERVOUS_SYSTEM", "DBTRG05MG_CENTRAL_NERVOUS_SYSTEM", 
  . "DEL_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "DETROIT562_UPPER_AERODIGESTIVE_TRACT", 
  . "DKMG_CENTRAL_NERVOUS_SYSTEM", "DMS114_LUNG", "DOHH2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "DOV13_OVARY", "DU145_PROSTATE", "DV90_LUNG", "EB1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "EB2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "EBC1_LUNG", "EFE184_ENDOMETRIUM", 
  . "EFM19_BREAST", "EFO21_OVARY", "EFO27_OVARY", "EM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "EN_ENDOMETRIUM", "ES2_OVARY", "ESS1_ENDOMETRIUM", "F36P_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "FADU_UPPER_AERODIGESTIVE_TRACT", "FU97_STOMACH", "FUOV1_OVARY", 
  . "G361_SKIN", "G401_SOFT_TISSUE", "G402_SOFT_TISSUE", "GAMG_CENTRAL_NERVOUS_SYSTEM", 
  . "GB1_CENTRAL_NERVOUS_SYSTEM", "GCIY_STOMACH", "GCT_SOFT_TISSUE", 
  . "GI1_CENTRAL_NERVOUS_SYSTEM", "GLC82_LUNG", "GMS10_CENTRAL_NERVOUS_SYSTEM", 
  . "GRANTA519_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "H4_CENTRAL_NERVOUS_SYSTEM", 
  . "HARA_LUNG", "HCC1187_BREAST", "HCC1395_BREAST", "HCC15_LUNG", 
  . "HCC1569_BREAST", "HCC1806_BREAST", "HCC1954_BREAST", "HCC2935_LUNG", 
  . "HCC4006_LUNG", "HCC44_LUNG", "HCC56_LARGE_INTESTINE", "HCC70_BREAST", 
  . "HCC78_LUNG", "HCC827_LUNG", "HCT116_LARGE_INTESTINE", "HCT15_LARGE_INTESTINE", 
  . "HDMYZ_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HDQP1_BREAST", "HEC151_ENDOMETRIUM", 
  . "HEC1A_ENDOMETRIUM", "HEC1B_ENDOMETRIUM", "HEC251_ENDOMETRIUM", 
  . "HEC265_ENDOMETRIUM", "HEC59_ENDOMETRIUM", "HEC6_ENDOMETRIUM", 
  . "HEL9217_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HEP3B217_LIVER", 
  . "HEPG2_LIVER", "HEYA8_OVARY", "HGC27_STOMACH", "HH_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "HLE_LIVER", "HLF_LIVER", "HMC18_BREAST", "HMCB_SKIN", "HOS_BONE", 
  . "HPAC_PANCREAS", "HPAFII_PANCREAS", "HS229T_LUNG", "HS294T_SKIN", 
  . "HS578T_BREAST", "HS683_CENTRAL_NERVOUS_SYSTEM", "HS695T_SKIN", 
  . "HS729_SOFT_TISSUE", "HS739T_BREAST", "HS746T_STOMACH", "HS766T_PANCREAS", 
  . "HS840T_UPPER_AERODIGESTIVE_TRACT", "HS852T_SKIN", "HS895T_SKIN", 
  . "HS936T_SKIN", "HS939T_SKIN", "HS944T_SKIN", "HSC2_UPPER_AERODIGESTIVE_TRACT", 
  . "HT_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HT1080_SOFT_TISSUE", 
  . "HT1197_URINARY_TRACT", "HT1376_URINARY_TRACT", "HT144_SKIN", 
  . "HT29_LARGE_INTESTINE", "HUCCT1_BILIARY_TRACT", "HUH1_LIVER", 
  . "HUPT3_PANCREAS", "HUPT4_PANCREAS", "HUT78_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "IALM_LUNG", "IGR37_SKIN", "IGR39_SKIN", "IGROV1_OVARY", "IM95_STOMACH", 
  . "IMR32_AUTONOMIC_GANGLIA", "IPC298_SKIN", "ISHIKAWAHERAKLIO02ER_ENDOMETRIUM", 
  . "ISTMES1_PLEURA", "ISTMES2_PLEURA", "J82_URINARY_TRACT", "JHH2_LIVER", 
  . "JHH4_LIVER", "JHH5_LIVER", "JHH6_LIVER", "JHH7_LIVER", "JHOS2_OVARY", 
  . "JHOS4_OVARY", "JHUEM2_ENDOMETRIUM", "JM1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "JMSU1_URINARY_TRACT", "JURKAT_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "JVM3_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "K029AX_SKIN", "KALS1_CENTRAL_NERVOUS_SYSTEM", 
  . "KARPAS299_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KARPAS422_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KARPAS620_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KASUMI2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KCIMOH1_PANCREAS", "KCL22_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KE39_STOMACH", "KE97_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KELLY_AUTONOMIC_GANGLIA", 
  . "KG1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KHM1B_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KLE_ENDOMETRIUM", "KMBC2_URINARY_TRACT", "KMM1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KMRC1_KIDNEY", "KMRC2_KIDNEY", "KMS11_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KMS12BM_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KMS26_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "KMS34_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KNS42_CENTRAL_NERVOUS_SYSTEM", 
  . "KNS60_CENTRAL_NERVOUS_SYSTEM", "KNS62_LUNG", "KNS81_CENTRAL_NERVOUS_SYSTEM", 
  . "KO52_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KP1N_PANCREAS", "KP1NL_PANCREAS", 
  . "KP2_PANCREAS", "KP3_PANCREAS", "KP4_PANCREAS", "KPNSI9S_AUTONOMIC_GANGLIA", 
  . "KU812_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KURAMOCHI_OVARY", 
  . "KYM1_SOFT_TISSUE", "KYSE140_OESOPHAGUS", "KYSE150_OESOPHAGUS", 
  . "KYSE180_OESOPHAGUS", "KYSE30_OESOPHAGUS", "KYSE410_OESOPHAGUS", 
  . "KYSE450_OESOPHAGUS", "KYSE510_OESOPHAGUS", "KYSE520_OESOPHAGUS", 
  . "KYSE70_OESOPHAGUS", "L33_PANCREAS", "L363_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "L428_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "LC1SQSF_LUNG", "LCLC103H_LUNG", 
  . "LN18_CENTRAL_NERVOUS_SYSTEM", "LN229_CENTRAL_NERVOUS_SYSTEM", 
  . "LOUNH91_LUNG", "LOXIMVI_SKIN", "LP1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "LS123_LARGE_INTESTINE", "LS411N_LARGE_INTESTINE", "LS513_LARGE_INTESTINE", 
  . "LU99_LUNG", "LUDLU1_LUNG", "M059J", "MALME3M_SKIN", "MB157_BREAST", 
  . "MC116_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MCAS_OVARY", "MCF7_BREAST", 
  . "MDAMB157_BREAST", "MDAMB175VII_BREAST", "MDAMB415_BREAST", "MDAMB435S_SKIN", 
  . "MDAMB436_BREAST", "MDAMB453_BREAST", "MDAMB468_BREAST", "MEC1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "MEG01_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MELHO_SKIN", "MESSA_SOFT_TISSUE", 
  . "MEWO_SKIN", "MFE280_ENDOMETRIUM", "MFE296_ENDOMETRIUM", "MFE319_ENDOMETRIUM", 
  . "MG63_BONE", "MHHES1_BONE", "MIAPACA2_PANCREAS", "MINO_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "MJ_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MKN45_STOMACH", "MKN7_STOMACH", 
  . "MKN74_STOMACH", "MOGGCCM_CENTRAL_NERVOUS_SYSTEM", "MOLP8_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "MOLT16_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MONOMAC1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "MORCPR_LUNG", "MPP89_PLEURA", "MSTO211H_PLEURA", "NCIH1048_LUNG", 
  . "NCIH1092_LUNG", "NCIH1155_LUNG", "NCIH1184_LUNG", "NCIH1299_LUNG", 
  . "NCIH1339_LUNG", "NCIH1341_LUNG", "NCIH1355_LUNG", "NCIH1373_LUNG", 
  . "NCIH1563_LUNG", "NCIH1568_LUNG", "NCIH1573_LUNG", "NCIH1581_LUNG", 
  . "NCIH1648_LUNG", "NCIH1650_LUNG", "NCIH1651_LUNG", "NCIH1666_LUNG", 
  . "NCIH1693_LUNG", "NCIH1694_LUNG", "NCIH1703_LUNG", "NCIH1792_LUNG", 
  . "NCIH1793_LUNG", "NCIH1869_LUNG", "NCIH1915_LUNG", "NCIH1944_LUNG", 
  . "NCIH1975_LUNG", "NCIH2009_LUNG", "NCIH2023_LUNG", "NCIH2030_LUNG", 
  . "NCIH2052_PLEURA", "NCIH2085_LUNG", "NCIH2087_LUNG", "NCIH211_LUNG", 
  . "NCIH2122_LUNG", "NCIH2170_LUNG", "NCIH2172_LUNG", "NCIH2228_LUNG", 
  . "NCIH226_LUNG", "NCIH2286_LUNG", "NCIH23_LUNG", "NCIH2444_LUNG", 
  . "NCIH2452_PLEURA", "NCIH28_PLEURA", "NCIH322_LUNG", "NCIH3255_LUNG", 
  . "NCIH358_LUNG", "NCIH441_LUNG", "NCIH460_LUNG", "NCIH520_LUNG", 
  . "NCIH522_LUNG", "NCIH647_LUNG", "NCIH650_LUNG", "NCIH661_LUNG", 
  . "NCIH727_LUNG", "NCIH747_LARGE_INTESTINE", "NCIH810_LUNG", "NCIN87_STOMACH", 
  . "NCO2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "NIHOVCAR3_OVARY", 
  . "NUGC3_STOMACH", "NUGC4_STOMACH", "OC314_OVARY", "OC315_OVARY", 
  . "OC316_OVARY", "OCIAML2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "OCIAML5_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "OCILY10_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "OCUM1_STOMACH", "OE21_OESOPHAGUS", "OE33_OESOPHAGUS", "ONCODG1_OVARY", 
  . "ONS76_CENTRAL_NERVOUS_SYSTEM", "OPM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "OV90_OVARY", "OVCAR4_OVARY", "OVCAR8_OVARY", "OVMANA_OVARY", 
  . "OVSAHO_OVARY", "OVTOKO_OVARY", "P12ICHIKAWA_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "P31FUJ_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "P3HR1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "PANC0203_PANCREAS", "PANC0327_PANCREAS", "PANC0403_PANCREAS", 
  . "PANC1005_PANCREAS", "PATU8902_PANCREAS", "PC14_LUNG", "PC3_PROSTATE", 
  . "PFEIFFER_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "PK1_PANCREAS", 
  . "PK45H_PANCREAS", "PK59_PANCREAS", "PL45_PANCREAS", "PLCPRF5_LIVER", 
  . "PSN1_PANCREAS", "QGP1_PANCREAS", "RAJI_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "RD_SOFT_TISSUE", "REH_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "RERFGC1B_STOMACH", 
  . "RERFLCAI_LUNG", "RERFLCMS_LUNG", "RKN_OVARY", "RKO_LARGE_INTESTINE", 
  . "RL952_ENDOMETRIUM", "RPMI7951_SKIN", "RPMI8402_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "RT112_URINARY_TRACT", "RT4_URINARY_TRACT", "RVH421_SKIN", "SAOS2_BONE", 
  . "SBC5_LUNG", "SCABER_URINARY_TRACT", "SCC9_UPPER_AERODIGESTIVE_TRACT", 
  . "SF126_CENTRAL_NERVOUS_SYSTEM", "SF295_CENTRAL_NERVOUS_SYSTEM", 
  . "SF8657", "SH10TC_STOMACH", "SHP77_LUNG", "SIGM5_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "SIMA_AUTONOMIC_GANGLIA", "SJRH30_SOFT_TISSUE", "SJSA1_BONE", 
  . "SKBR3_BREAST", "SKCO1_LARGE_INTESTINE", "SKES1_BONE", "SKHEP1_LIVER", 
  . "SKLMS1_SOFT_TISSUE", "SKLU1_LUNG", "SKMEL2_SKIN", "SKMEL24_SKIN", 
  . "SKMEL30_SKIN", "SKMEL31_SKIN", "SKMEL5_SKIN", "SKMES1_LUNG", 
  . "SKMM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SKNAS_AUTONOMIC_GANGLIA", 
  . "SKNBE2_AUTONOMIC_GANGLIA", "SKNDZ_AUTONOMIC_GANGLIA", "SKNFI_AUTONOMIC_GANGLIA", 
  . "SKNSH_AUTONOMIC_GANGLIA", "SKOV3_OVARY", "SNGM_ENDOMETRIUM", 
  . "SNU1_STOMACH", "SNU16_STOMACH", "SNU182_LIVER", "SNU387_LIVER", 
  . "SNU398_LIVER", "SNU423_LIVER", "SNU449_LIVER", "SNU475_LIVER", 
  . "SNUC2A_LARGE_INTESTINE", "SNUC2B", "SQ1_LUNG", "SU8686_PANCREAS", 
  . "SUDHL10_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SUDHL4_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "SUDHL6_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SUDHL8_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "SUIT2_PANCREAS", "SUPM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "SUPT1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SW1088_CENTRAL_NERVOUS_SYSTEM", 
  . "SW1271_LUNG", "SW1353_BONE", "SW1417_LARGE_INTESTINE", "SW1573_LUNG", 
  . "SW1990_PANCREAS", "SW403_LARGE_INTESTINE", "SW48_LARGE_INTESTINE", 
  . "SW480_LARGE_INTESTINE", "SW579_THYROID", "SW620_LARGE_INTESTINE", 
  . "SW780_URINARY_TRACT", "SW900_LUNG", "T24_URINARY_TRACT", "T3M10_LUNG", 
  . "T47D_BREAST", "T84_LARGE_INTESTINE", "T98G_CENTRAL_NERVOUS_SYSTEM", 
  . "TC71_BONE", "TCCSUP_URINARY_TRACT", "TE1_OESOPHAGUS", "TE11_OESOPHAGUS", 
  . "TE15_OESOPHAGUS", "TE5_OESOPHAGUS", "TE617T_SOFT_TISSUE", "TE9_OESOPHAGUS", 
  . "TEN_ENDOMETRIUM", "TOLEDO_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  . "TOV112D_OVARY", "TOV21G_OVARY", "TT2609C02_THYROID", "TYKNU_OVARY", 
  . "U118MG_CENTRAL_NERVOUS_SYSTEM", "U2OS_BONE", "U87MG_CENTRAL_NERVOUS_SYSTEM", 
  . "U937_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "UACC257_SKIN", "UACC62_SKIN", 
  . "UACC812_BREAST", "UMUC3_URINARY_TRACT", "VMRCLCD_LUNG", "VMRCRCW_KIDNEY", 
  . "VMRCRCZ_KIDNEY", "WM115_SKIN", "WM1799_SKIN", "WM2664_SKIN", 
  . "WM793_SKIN", "WM88_SKIN", "WM983B_SKIN", "YKG1_CENTRAL_NERVOUS_SYSTEM", 
  . "ZR751_BREAST", "ZR7530_BREAST"), subscript_type = "character", 
  .     names = c("Name", "Description", "22RV1_PROSTATE", "2313287_STOMACH", 
  .     "253JBV_URINARY_TRACT", "253J_URINARY_TRACT", "42MGBA_CENTRAL_NERVOUS_SYSTEM", 
  .     "5637_URINARY_TRACT", "59M_OVARY", "639V_URINARY_TRACT", 
  .     "647V_URINARY_TRACT", "697_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "769P_KIDNEY", "786O_KIDNEY", "8305C_THYROID", "8505C_THYROID", 
  .     "8MGBA_CENTRAL_NERVOUS_SYSTEM", "A101D_SKIN", "A1207_CENTRAL_NERVOUS_SYSTEM", 
  .     "A172_CENTRAL_NERVOUS_SYSTEM", "A204_SOFT_TISSUE", "A2058_SKIN", 
  .     "A253_SALIVARY_GLAND", "A2780_OVARY", "A375_SKIN", "A3KAW_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "A427_LUNG", "A498_KIDNEY", "A4FUK_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "A549_LUNG", "A673_BONE", "A704_KIDNEY", "ABC1_LUNG", "ACCMESO1_PLEURA", 
  .     "ACHN_KIDNEY", "AGS_STOMACH", "ALLSIL_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "AM38_CENTRAL_NERVOUS_SYSTEM", "AML193_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "AMO1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "AN3CA_ENDOMETRIUM", 
  .     "ASPC1_PANCREAS", "AU565_BREAST", "BC3C_URINARY_TRACT", "BCP1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "BCPAP_THYROID", "BDCM_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "BEN_LUNG", "BFTC905_URINARY_TRACT", "BFTC909_KIDNEY", "BHT101_THYROID", 
  .     "BHY_UPPER_AERODIGESTIVE_TRACT", "BICR16_UPPER_AERODIGESTIVE_TRACT", 
  .     "BICR18_UPPER_AERODIGESTIVE_TRACT", "BICR22_UPPER_AERODIGESTIVE_TRACT", 
  .     "BICR31_UPPER_AERODIGESTIVE_TRACT", "BICR56_UPPER_AERODIGESTIVE_TRACT", 
  .     "BICR6_UPPER_AERODIGESTIVE_TRACT", "BL41_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "BL70_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "BT12_SOFT_TISSUE", 
  .     "BT20_BREAST", "BT474_BREAST", "BT483_BREAST", "BT549_BREAST", 
  .     "BV173_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "BXPC3_PANCREAS", 
  .     "C2BBE1_LARGE_INTESTINE", "C32_SKIN", "C8166_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "CA46_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "CADOES1_BONE", 
  .     "CAKI1_KIDNEY", "CAKI2_KIDNEY", "CAL120_BREAST", "CAL12T_LUNG", 
  .     "CAL148_BREAST", "CAL27_UPPER_AERODIGESTIVE_TRACT", "CAL29_URINARY_TRACT", 
  .     "CAL33_UPPER_AERODIGESTIVE_TRACT", "CAL51_BREAST", "CAL54_KIDNEY", 
  .     "CAL62_THYROID", "CAL78_BONE", "CAL851_BREAST", "CALU1_LUNG", 
  .     "CALU3_LUNG", "CALU6_LUNG", "CAMA1_BREAST", "CAOV3_OVARY", 
  .     "CAOV4_OVARY", "CAPAN1_PANCREAS", "CAPAN2_PANCREAS", "CAS1_CENTRAL_NERVOUS_SYSTEM", 
  .     "CCFSTTG1_CENTRAL_NERVOUS_SYSTEM", "CCK81_LARGE_INTESTINE", 
  .     "CFPAC1_PANCREAS", "CH157MN_CENTRAL_NERVOUS_SYSTEM", "CHAGOK1_LUNG", 
  .     "CHP126_AUTONOMIC_GANGLIA", "CHP212_AUTONOMIC_GANGLIA", "CI1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "CJM_SKIN", "CL11_LARGE_INTESTINE", "CL14_LARGE_INTESTINE", 
  .     "CL34_LARGE_INTESTINE", "CL40_LARGE_INTESTINE", "CMK_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "CMLT1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "COLO201_LARGE_INTESTINE", 
  .     "COLO320_LARGE_INTESTINE", "COLO668_LUNG", "COLO678_LARGE_INTESTINE", 
  .     "COLO679_SKIN", "COLO680N_OESOPHAGUS", "COLO684_ENDOMETRIUM", 
  .     "COLO741_SKIN", "COLO783_SKIN", "COLO792_SKIN", "COLO800_SKIN", 
  .     "COLO829_SKIN", "CORL105_LUNG", "CORL23_LUNG", "CORL24_LUNG", 
  .     "CORL279_LUNG", "CORL311_LUNG", "CORL47_LUNG", "CORL88_LUNG", 
  .     "CORL95_LUNG", "COV318_OVARY", "COV362_OVARY", "COV434_OVARY", 
  .     "COV644_OVARY", "CW2_LARGE_INTESTINE", "CACO2_LARGE_INTESTINE", 
  .     "D283MED_CENTRAL_NERVOUS_SYSTEM", "D341MED_CENTRAL_NERVOUS_SYSTEM", 
  .     "DANG_PANCREAS", "DAOY_CENTRAL_NERVOUS_SYSTEM", "DAUDI_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "DBTRG05MG_CENTRAL_NERVOUS_SYSTEM", "DB_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "DEL_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "DETROIT562_UPPER_AERODIGESTIVE_TRACT", 
  .     "DKMG_CENTRAL_NERVOUS_SYSTEM", "DM3_FIBROBLAST", "DMS114_LUNG", 
  .     "DMS153_LUNG", "DMS273_LUNG", "DMS454_LUNG", "DMS53_LUNG", 
  .     "DMS79_LUNG", "DND41_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "DOHH2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "DU145_PROSTATE", 
  .     "DU4475_BREAST", "DV90_LUNG", "EB1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "EBC1_LUNG", "ECC10_STOMACH", "ECC12_STOMACH", "ECGI10_OESOPHAGUS", 
  .     "EFE184_ENDOMETRIUM", "EFM192A_BREAST", "EFM19_BREAST", "EFO21_OVARY", 
  .     "EFO27_OVARY", "EHEB_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "EJM_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "EKVX_LUNG", "EM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "EN_ENDOMETRIUM", "EOL1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "EPLC272H_LUNG", "ES2_OVARY", "ESS1_ENDOMETRIUM", "EW8_BONE", 
  .     "EWS502_BONE", "F36P_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "FADU_UPPER_AERODIGESTIVE_TRACT", "FTC133_THYROID", "FTC238_THYROID", 
  .     "FU97_STOMACH", "FUOV1_OVARY", "G292CLONEA141B1_BONE", "G361_SKIN", 
  .     "G401_SOFT_TISSUE", "G402_SOFT_TISSUE", "GA10_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "GAMG_CENTRAL_NERVOUS_SYSTEM", "GB1_CENTRAL_NERVOUS_SYSTEM", 
  .     "GCIY_STOMACH", "GCT_SOFT_TISSUE", "GDM1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "GI1_CENTRAL_NERVOUS_SYSTEM", "GMS10_CENTRAL_NERVOUS_SYSTEM", 
  .     "GOS3_CENTRAL_NERVOUS_SYSTEM", "GP2D_LARGE_INTESTINE", "GRANTA519_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "GSS_STOMACH", "GSU_STOMACH", "H4_CENTRAL_NERVOUS_SYSTEM", 
  .     "HARA_LUNG", "HCC1143_BREAST", "HCC1171_LUNG", "HCC1187_BREAST", 
  .     "HCC1195_LUNG", "HCC1359_LUNG", "HCC1395_BREAST", "HCC1419_BREAST", 
  .     "HCC1428_BREAST", "HCC1438_LUNG", "HCC1500_BREAST", "HCC1569_BREAST", 
  .     "HCC1588_LUNG", "HCC1599_BREAST", "HCC15_LUNG", "HCC1806_BREAST", 
  .     "HCC1833_LUNG", "HCC1937_BREAST", "HCC1954_BREAST", "HCC202_BREAST", 
  .     "HCC2108_LUNG", "HCC2157_BREAST", "HCC2218_BREAST", "HCC2279_LUNG", 
  .     "HCC2429_LUNG", "HCC2450_LUNG", "HCC2814_LUNG", "HCC2935_LUNG", 
  .     "HCC33_LUNG", "HCC364_LUNG", "HCC366_LUNG", "HCC38_BREAST", 
  .     "HCC4006_LUNG", "HCC44_LUNG", "HCC461_LUNG", "HCC515_LUNG", 
  .     "HCC56_LARGE_INTESTINE", "HCC70_BREAST", "HCC78_LUNG", "HCC827GR5_LUNG", 
  .     "HCC827_LUNG", "HCC95_LUNG", "HCT116_LARGE_INTESTINE", "HCT15_LARGE_INTESTINE", 
  .     "HDLM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HDMYZ_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "HDQP1_BREAST", "HEC108_ENDOMETRIUM", "HEC151_ENDOMETRIUM", 
  .     "HEC1A_ENDOMETRIUM", "HEC1B_ENDOMETRIUM", "HEC251_ENDOMETRIUM", 
  .     "HEC265_ENDOMETRIUM", "HEC50B_ENDOMETRIUM", "HEC59_ENDOMETRIUM", 
  .     "HEC6_ENDOMETRIUM", "HEKTE_KIDNEY", "HEL9217_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "HEL_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HEP3B217_LIVER", 
  .     "HEPG2_LIVER", "HEYA8_OVARY", "HGC27_STOMACH", "HH_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "HL60_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HLFA_FIBROBLAST", 
  .     "HLF_LIVER", "HMC18_BREAST", "HMCB_SKIN", "HMEL_BREAST", 
  .     "HNT34_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HOP62_LUNG", 
  .     "HOP92_LUNG", "HOS_BONE", "HPAC_PANCREAS", "HPAFII_PANCREAS", 
  .     "HPBALL_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HS172T_FIBROBLAST", 
  .     "HS229T_FIBROBLAST", "HS255T_FIBROBLAST", "HS274T_BREAST", 
  .     "HS281T_FIBROBLAST", "HS294T_SKIN", "HS343T_FIBROBLAST", 
  .     "HS578T_BREAST", "HS600T_FIBROBLAST", "HS606T_FIBROBLAST", 
  .     "HS611T_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HS616T_FIBROBLAST", 
  .     "HS618T_FIBROBLAST", "HS675T_FIBROBLAST", "HS683_CENTRAL_NERVOUS_SYSTEM", 
  .     "HS688AT_FIBROBLAST", "HS695T_SKIN", "HS698T_FIBROBLAST", 
  .     "HS706T_BONE", "HS729_SOFT_TISSUE", "HS737T_FIBROBLAST", 
  .     "HS739T_FIBROBLAST", "HS742T_FIBROBLAST", "HS746T_STOMACH", 
  .     "HS751T_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HS766T_PANCREAS", 
  .     "HS819T_FIBROBLAST", "HS821T_FIBROBLAST", "HS822T_FIBROBLAST", 
  .     "HS834T_FIBROBLAST", "HS839T_FIBROBLAST", "HS840T_FIBROBLAST", 
  .     "HS852T_SKIN", "HS863T_FIBROBLAST", "HS870T_FIBROBLAST", 
  .     "HS888T_FIBROBLAST", "HS895T_FIBROBLAST", "HS934T_FIBROBLAST", 
  .     "HS936T_SKIN", "HS939T_SKIN", "HS940T_FIBROBLAST", "HS944T_SKIN", 
  .     "HSC2_UPPER_AERODIGESTIVE_TRACT", "HSC3_UPPER_AERODIGESTIVE_TRACT", 
  .     "HSC4_UPPER_AERODIGESTIVE_TRACT", "HT1080_SOFT_TISSUE", "HT115_LARGE_INTESTINE", 
  .     "HT1197_URINARY_TRACT", "HT1376_URINARY_TRACT", "HT144_SKIN", 
  .     "HT29_LARGE_INTESTINE", "HT55_LARGE_INTESTINE", "HT_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "HUCCT1_BILIARY_TRACT", "HUG1N_STOMACH", "HUH1_LIVER", "HUH28_BILIARY_TRACT", 
  .     "HUH6_LIVER", "HUH7_LIVER", "HUNS1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "HUPT3_PANCREAS", "HUPT4_PANCREAS", "HUT102_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "HUT78_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "HUTU80_SMALL_INTESTINE", 
  .     "HELA_CERVIX", "IALM_LUNG", "IGR1_SKIN", "IGR37_SKIN", "IGR39_SKIN", 
  .     "IGROV1_OVARY", "IM95_STOMACH", "IMR32_AUTONOMIC_GANGLIA", 
  .     "INA6_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "IOMMLEE_CENTRAL_NERVOUS_SYSTEM", 
  .     "IPC298_SKIN", "ISHIKAWAHERAKLIO02ER_ENDOMETRIUM", "ISTMES1_PLEURA", 
  .     "ISTMES2_PLEURA", "J82_URINARY_TRACT", "JEKO1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "JHESOAD1_OESOPHAGUS", "JHH1_LIVER", "JHH2_LIVER", "JHH4_LIVER", 
  .     "JHH5_LIVER", "JHH6_LIVER", "JHH7_LIVER", "JHOC5_OVARY", 
  .     "JHOM1_OVARY", "JHOM2B_OVARY", "JHOS2_OVARY", "JHOS4_OVARY", 
  .     "JHUEM1_ENDOMETRIUM", "JHUEM2_ENDOMETRIUM", "JHUEM3_ENDOMETRIUM", 
  .     "JHUEM7_ENDOMETRIUM", "JIMT1_BREAST", "JJN3_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "JK1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "JL1_PLEURA", "JM1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "JMSU1_URINARY_TRACT", "JURKAT_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "JURLMK1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "JVM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "JVM3_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "K029AX_SKIN", 
  .     "K562_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KALS1_CENTRAL_NERVOUS_SYSTEM", 
  .     "KARPAS299_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KARPAS422_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KARPAS620_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KASUMI1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KASUMI2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KASUMI6_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KATOIII_STOMACH", "KCL22_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KD_SOFT_TISSUE", "KE37_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KE39_STOMACH", "KE97_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KELLY_AUTONOMIC_GANGLIA", "KG1C_CENTRAL_NERVOUS_SYSTEM", 
  .     "KG1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KHM1B_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KIJK_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KLE_ENDOMETRIUM", 
  .     "KM12_LARGE_INTESTINE", "KMBC2_URINARY_TRACT", "KMH2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KMM1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KMRC1_KIDNEY", 
  .     "KMRC20_KIDNEY", "KMRC2_KIDNEY", "KMRC3_KIDNEY", "KMS18_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KMS11_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KMS12BM_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KMS20_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KMS21BM_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KMS26_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KMS27_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KMS28BM_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KMS34_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KNS42_CENTRAL_NERVOUS_SYSTEM", "KNS60_CENTRAL_NERVOUS_SYSTEM", 
  .     "KNS62_LUNG", "KNS81_CENTRAL_NERVOUS_SYSTEM", "KO52_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KOPN8_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "KP2_PANCREAS", 
  .     "KP3_PANCREAS", "KP4_PANCREAS", "KPL1_BREAST", "KPMRTRY_SOFT_TISSUE", 
  .     "KPNRTBM1_AUTONOMIC_GANGLIA", "KPNSI9S_AUTONOMIC_GANGLIA", 
  .     "KPNYN_AUTONOMIC_GANGLIA", "KS1_CENTRAL_NERVOUS_SYSTEM", 
  .     "KU1919_URINARY_TRACT", "KU812_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KURAMOCHI_OVARY", "KYM1_SOFT_TISSUE", "KYO1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "KYSE140_OESOPHAGUS", "KYSE150_OESOPHAGUS", "KYSE180_OESOPHAGUS", 
  .     "KYSE270_OESOPHAGUS", "KYSE30_OESOPHAGUS", "KYSE410_OESOPHAGUS", 
  .     "KYSE450_OESOPHAGUS", "KYSE510_OESOPHAGUS", "KYSE520_OESOPHAGUS", 
  .     "KYSE70_OESOPHAGUS", "L1236_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "L33_PANCREAS", "L363_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "L428_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "L540_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "LAMA84_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "LC1F_LUNG", 
  .     "LCLC103H_LUNG", "LCLC97TM1_LUNG", "LI7_LIVER", "LK2_LUNG", 
  .     "LMSU_STOMACH", "LN18_CENTRAL_NERVOUS_SYSTEM", "LN215_CENTRAL_NERVOUS_SYSTEM", 
  .     "LN229_CENTRAL_NERVOUS_SYSTEM", "LN235_CENTRAL_NERVOUS_SYSTEM", 
  .     "LN319_CENTRAL_NERVOUS_SYSTEM", "LN340_CENTRAL_NERVOUS_SYSTEM", 
  .     "LN382_CENTRAL_NERVOUS_SYSTEM", "LN428_CENTRAL_NERVOUS_SYSTEM", 
  .     "LN443_CENTRAL_NERVOUS_SYSTEM", "LN464_CENTRAL_NERVOUS_SYSTEM", 
  .     "LNCAPCLONEFGC_PROSTATE", "LNZ308_CENTRAL_NERVOUS_SYSTEM", 
  .     "LOUCY_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "LOUNH91_LUNG", 
  .     "LOVO_LARGE_INTESTINE", "LOXIMVI_SKIN", "LP1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "LS1034_LARGE_INTESTINE", "LS123_LARGE_INTESTINE", "LS180_LARGE_INTESTINE", 
  .     "LS411N_LARGE_INTESTINE", "LS513_LARGE_INTESTINE", "LU65_LUNG", 
  .     "LU99_LUNG", "LUDLU1_LUNG", "LXF289_LUNG", "M059K_CENTRAL_NERVOUS_SYSTEM", 
  .     "M07E_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MALME3M_SKIN", 
  .     "MC116_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MCAS_OVARY", 
  .     "MCF7_BREAST", "MDAMB134VI_BREAST", "MDAMB157_BREAST", "MDAMB175VII_BREAST", 
  .     "MDAMB231_BREAST", "MDAMB361_BREAST", "MDAMB415_BREAST", 
  .     "MDAMB435S_SKIN", "MDAMB436_BREAST", "MDAMB453_BREAST", "MDAMB468_BREAST", 
  .     "MDAPCA2B_PROSTATE", "MDST8_LARGE_INTESTINE", "ME1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "MEC1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MEG01_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "MELHO_SKIN", "MELJUSO_SKIN", "MESSA_SOFT_TISSUE", "MEWO_SKIN", 
  .     "MFE280_ENDOMETRIUM", "MFE296_ENDOMETRIUM", "MFE319_ENDOMETRIUM", 
  .     "MG63_BONE", "MHHCALL2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "MHHCALL3_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MHHCALL4_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "MHHES1_BONE", "MHHNB11_AUTONOMIC_GANGLIA", "MIAPACA2_PANCREAS", 
  .     "MINO_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MJ_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "MKN1_STOMACH", "MKN45_STOMACH", "MKN74_STOMACH", "MKN7_STOMACH", 
  .     "ML1_THYROID", "MM1S_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "MOLM13_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MOLM16_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "MOLM6_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MOLP2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "MOLP8_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MOLT13_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "MOLT16_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MOLT3_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "MON_SOFT_TISSUE", "MONOMAC1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "MONOMAC6_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MORCPR_LUNG", 
  .     "MPP89_PLEURA", "MSTO211H_PLEURA", "MUTZ3_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "MUTZ5_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MV411_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "NALM19_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "NALM1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "NALM6_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "NAMALWA_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "NB1_AUTONOMIC_GANGLIA", "NB4_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "NCCSTCK140_STOMACH", "NCIH2004RT_SOFT_TISSUE", "NCIH2077_LUNG", 
  .     "NCIH2882_LUNG", "NCIH2887_LUNG", "NCIH1048_LUNG", "NCIH1092_LUNG", 
  .     "NCIH1105_LUNG", "NCIH1155_LUNG", "NCIH1184_LUNG", "NCIH1299_LUNG", 
  .     "NCIH1339_LUNG", "NCIH1341_LUNG", "NCIH1355_LUNG", "NCIH1373_LUNG", 
  .     "NCIH1385_LUNG", "NCIH1395_LUNG", "NCIH1435_LUNG", "NCIH1436_LUNG", 
  .     "NCIH1437_LUNG", "NCIH146_LUNG", "NCIH1563_LUNG", "NCIH1568_LUNG", 
  .     "NCIH1573_LUNG", "NCIH1581_LUNG", "NCIH1618_LUNG", "NCIH1623_LUNG", 
  .     "NCIH1648_LUNG", "NCIH1650_LUNG", "NCIH1651_LUNG", "NCIH1666_LUNG", 
  .     "NCIH1693_LUNG", "NCIH1694_LUNG", "NCIH1703_LUNG", "NCIH1734_LUNG", 
  .     "NCIH1755_LUNG", "NCIH1781_LUNG", "NCIH1792_LUNG", "NCIH1793_LUNG", 
  .     "NCIH1819_LUNG", "NCIH1836_LUNG", "NCIH1838_LUNG", "NCIH1869_LUNG", 
  .     "NCIH1876_LUNG", "NCIH1915_LUNG", "NCIH1930_LUNG", "NCIH1944_LUNG", 
  .     "NCIH1963_LUNG", "NCIH196_LUNG", "NCIH1975_LUNG", "NCIH2009_LUNG", 
  .     "NCIH2023_LUNG", "NCIH2029_LUNG", "NCIH2030_LUNG", "NCIH2052_PLEURA", 
  .     "NCIH2066_LUNG", "NCIH2073_LUNG", "NCIH2081_LUNG", "NCIH2085_LUNG", 
  .     "NCIH2087_LUNG", "NCIH209_LUNG", "NCIH2106_LUNG", "NCIH2110_LUNG", 
  .     "NCIH211_LUNG", "NCIH2122_LUNG", "NCIH2126_LUNG", "NCIH2170_LUNG", 
  .     "NCIH2171_LUNG", "NCIH2172_LUNG", "NCIH2196_LUNG", "NCIH2227_LUNG", 
  .     "NCIH2228_LUNG", "NCIH226_LUNG", "NCIH2286_LUNG", "NCIH2291_LUNG", 
  .     "NCIH2342_LUNG", "NCIH2347_LUNG", "NCIH23_LUNG", "NCIH2405_LUNG", 
  .     "NCIH2444_LUNG", "NCIH2452_PLEURA", "NCIH28_PLEURA", "NCIH292_LUNG", 
  .     "NCIH3122_LUNG", "NCIH322_LUNG", "NCIH3255_LUNG", "NCIH358_LUNG", 
  .     "NCIH441_LUNG", "NCIH446_LUNG", "NCIH460_LUNG", "NCIH508_LARGE_INTESTINE", 
  .     "NCIH510_LUNG", "NCIH520_LUNG", "NCIH522_LUNG", "NCIH524_LUNG", 
  .     "NCIH526_LUNG", "NCIH596_LUNG", "NCIH647_LUNG", "NCIH650_LUNG", 
  .     "NCIH660_PROSTATE", "NCIH661_LUNG", "NCIH684_LIVER", "NCIH69_LUNG", 
  .     "NCIH716_LARGE_INTESTINE", "NCIH727_LUNG", "NCIH747_LARGE_INTESTINE", 
  .     "NCIH810_LUNG", "NCIH82_LUNG", "NCIH838_LUNG", "NCIH841_LUNG", 
  .     "NCIH854_LUNG", "NCIH889_LUNG", "NCIH929_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "NCIN87_STOMACH", "NCO2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "NH6_AUTONOMIC_GANGLIA", "NHAHTDD_CENTRAL_NERVOUS_SYSTEM", 
  .     "NIHOVCAR3_OVARY", "NMCG1_CENTRAL_NERVOUS_SYSTEM", "NOMO1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "NUDHL1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "NUDUL1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "NUGC2_STOMACH", "NUGC3_STOMACH", "NUGC4_STOMACH", "OAW28_OVARY", 
  .     "OAW42_OVARY", "OC314_OVARY", "OCIMY5_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "OCIMY7_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "OCIAML2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "OCIAML3_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "OCIAML5_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "OCILY19_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "OCILY3_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "OCIM1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "OCUM1_STOMACH", 
  .     "OE19_OESOPHAGUS", "OE21_OESOPHAGUS", "OE33_OESOPHAGUS", 
  .     "OELE_OVARY", "ONCODG1_OVARY", "ONS76_CENTRAL_NERVOUS_SYSTEM", 
  .     "OPM1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "OPM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "OSRC2_KIDNEY", "OUMS23_LARGE_INTESTINE", "OV56_OVARY", "OV7_OVARY", 
  .     "OV90_OVARY", "OVCAR4_OVARY", "OVCAR8_OVARY", "OVISE_OVARY", 
  .     "OVK18_OVARY", "OVKATE_OVARY", "OVMANA_OVARY", "OVSAHO_OVARY", 
  .     "OVTOKO_OVARY", "P12ICHIKAWA_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "P31FUJ_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "P3HR1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "PANC0203_PANCREAS", "PANC0213_PANCREAS", "PANC0327_PANCREAS", 
  .     "PANC0403_PANCREAS", "PANC0504_PANCREAS", "PANC0813_PANCREAS", 
  .     "PANC1005_PANCREAS", "PANC1_PANCREAS", "PATU8902_PANCREAS", 
  .     "PATU8988S_PANCREAS", "PATU8988T_PANCREAS", "PC9_LUNG", "PC14_LUNG", 
  .     "PC3_PROSTATE", "PECAPJ15_UPPER_AERODIGESTIVE_TRACT", "PECAPJ34CLONEC12_UPPER_AERODIGESTIVE_TRACT", 
  .     "PECAPJ41CLONED2_UPPER_AERODIGESTIVE_TRACT", "PECAPJ49_UPPER_AERODIGESTIVE_TRACT", 
  .     "PEER_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "PF382_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "PFEIFFER_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "PK1_PANCREAS", 
  .     "PK45H_PANCREAS", "PK59_PANCREAS", "PL21_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "PLB985_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "PLCPRF5_LIVER", 
  .     "PRECLH_PROSTATE", "PSN1_PANCREAS", "QGP1_PANCREAS", "RAJI_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "RCC10RGB_KIDNEY", "RCHACV_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "RCM1_LARGE_INTESTINE", "RDES_BONE", "RD_SOFT_TISSUE", "REC1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "REH_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "RERFGC1B_STOMACH", 
  .     "RERFLCAD1_LUNG", "RERFLCAD2_LUNG", "RERFLCAI_LUNG", "RERFLCKJ_LUNG", 
  .     "RERFLCMS_LUNG", "RERFLCSQ1_LUNG", "RH18_SOFT_TISSUE", "RH30_SOFT_TISSUE", 
  .     "RH41_SOFT_TISSUE", "RI1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "RKN_SOFT_TISSUE", "RKO_LARGE_INTESTINE", "RL952_ENDOMETRIUM", 
  .     "RL_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "RMGI_OVARY", "RMUGS_OVARY", 
  .     "RPMI7951_SKIN", "RPMI8226_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "RPMI8402_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "RS411_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "RS5_FIBROBLAST", "RT112_URINARY_TRACT", "RT4_URINARY_TRACT", 
  .     "RVH421_SKIN", "S117_SOFT_TISSUE", "SALE_LUNG", "SAOS2_BONE", 
  .     "SBC5_LUNG", "SCABER_URINARY_TRACT", "SCC15_UPPER_AERODIGESTIVE_TRACT", 
  .     "SCC25_UPPER_AERODIGESTIVE_TRACT", "SCC4_UPPER_AERODIGESTIVE_TRACT", 
  .     "SCC9_UPPER_AERODIGESTIVE_TRACT", "SCLC21H_LUNG", "SEM_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "SET2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SF126_CENTRAL_NERVOUS_SYSTEM", 
  .     "SF172_CENTRAL_NERVOUS_SYSTEM", "SF268_CENTRAL_NERVOUS_SYSTEM", 
  .     "SF295_CENTRAL_NERVOUS_SYSTEM", "SF539_CENTRAL_NERVOUS_SYSTEM", 
  .     "SF767_CENTRAL_NERVOUS_SYSTEM", "SH10TC_STOMACH", "SH4_SKIN", 
  .     "SHP77_LUNG", "SIGM5_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "SIMA_AUTONOMIC_GANGLIA", "SJSA1_BONE", "SKBR3_BREAST", "SKCO1_LARGE_INTESTINE", 
  .     "SKES1_BONE", "SKHEP1_LIVER", "SKLMS1_SOFT_TISSUE", "SKLU1_LUNG", 
  .     "SKM1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SKMEL1_SKIN", 
  .     "SKMEL24_SKIN", "SKMEL28_SKIN", "SKMEL30_SKIN", "SKMEL31_SKIN", 
  .     "SKMEL3_SKIN", "SKMEL5_SKIN", "SKMES1_LUNG", "SKMM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "SKNAS_AUTONOMIC_GANGLIA", "SKNBE2_AUTONOMIC_GANGLIA", "SKNDZ_AUTONOMIC_GANGLIA", 
  .     "SKNEP1_BONE", "SKNFI_AUTONOMIC_GANGLIA", "SKNMC_BONE", "SKNO1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "SKNSH_AUTONOMIC_GANGLIA", "SKOV3_OVARY", "SKPNDW_BONE", 
  .     "SKRC20_KIDNEY", "SKUT1_SOFT_TISSUE", "SLR20_KIDNEY", "SLR21_KIDNEY", 
  .     "SLR23_KIDNEY", "SLR24_KIDNEY", "SLR25_KIDNEY", "SLR26_KIDNEY", 
  .     "SNB75_CENTRAL_NERVOUS_SYSTEM", "SNGM_ENDOMETRIUM", "SNU1033_LARGE_INTESTINE", 
  .     "SNU1040_LARGE_INTESTINE", "SNU1041_UPPER_AERODIGESTIVE_TRACT", 
  .     "SNU1066_UPPER_AERODIGESTIVE_TRACT", "SNU1076_UPPER_AERODIGESTIVE_TRACT", 
  .     "SNU1077_ENDOMETRIUM", "SNU1079_BILIARY_TRACT", "SNU1105_CENTRAL_NERVOUS_SYSTEM", 
  .     "SNU1196_BILIARY_TRACT", "SNU1197_LARGE_INTESTINE", "SNU119_OVARY", 
  .     "SNU1214_UPPER_AERODIGESTIVE_TRACT", "SNU1272_KIDNEY", "SNU16_STOMACH", 
  .     "SNU175_LARGE_INTESTINE", "SNU182_LIVER", "SNU1_STOMACH", 
  .     "SNU201_CENTRAL_NERVOUS_SYSTEM", "SNU213_PANCREAS", "SNU216_STOMACH", 
  .     "SNU245_BILIARY_TRACT", "SNU283_LARGE_INTESTINE", "SNU308_BILIARY_TRACT", 
  .     "SNU324_PANCREAS", "SNU349_KIDNEY", "SNU387_LIVER", "SNU398_LIVER", 
  .     "SNU407_LARGE_INTESTINE", "SNU410_PANCREAS", "SNU423_LIVER", 
  .     "SNU449_LIVER", "SNU466_CENTRAL_NERVOUS_SYSTEM", "SNU46_UPPER_AERODIGESTIVE_TRACT", 
  .     "SNU475_LIVER", "SNU478_BILIARY_TRACT", "SNU489_CENTRAL_NERVOUS_SYSTEM", 
  .     "SNU503_LARGE_INTESTINE", "SNU520_STOMACH", "SNU5_STOMACH", 
  .     "SNU601_STOMACH", "SNU61_LARGE_INTESTINE", "SNU620_STOMACH", 
  .     "SNU626_CENTRAL_NERVOUS_SYSTEM", "SNU668_STOMACH", "SNU685_ENDOMETRIUM", 
  .     "SNU719_STOMACH", "SNU738_CENTRAL_NERVOUS_SYSTEM", "SNU761_LIVER", 
  .     "SNU81_LARGE_INTESTINE", "SNU840_OVARY", "SNU869_BILIARY_TRACT", 
  .     "SNU878_LIVER", "SNU886_LIVER", "SNU899_UPPER_AERODIGESTIVE_TRACT", 
  .     "SNU8_OVARY", "SNUC1_LARGE_INTESTINE", "SNUC2A_LARGE_INTESTINE", 
  .     "SNUC4_LARGE_INTESTINE", "SNUC5_LARGE_INTESTINE", "SQ1_LUNG", 
  .     "SR786_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "ST486_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "STM9101_SOFT_TISSUE", "SU8686_PANCREAS", "SUDHL10_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "SUDHL1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SUDHL4_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "SUDHL5_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SUDHL6_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "SUDHL8_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SUIT2_PANCREAS", 
  .     "SUPB15_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SUPM2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "SUPT11_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "SUPT1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "SW1088_CENTRAL_NERVOUS_SYSTEM", "SW1116_LARGE_INTESTINE", 
  .     "SW1271_LUNG", "SW1353_BONE", "SW1417_LARGE_INTESTINE", "SW1463_LARGE_INTESTINE", 
  .     "SW1573_LUNG", "SW1710_URINARY_TRACT", "SW1783_CENTRAL_NERVOUS_SYSTEM", 
  .     "SW1990_PANCREAS", "SW403_LARGE_INTESTINE", "SW480_LARGE_INTESTINE", 
  .     "SW48_LARGE_INTESTINE", "SW579_THYROID", "SW620_LARGE_INTESTINE", 
  .     "SW780_URINARY_TRACT", "SW837_LARGE_INTESTINE", "SW900_LUNG", 
  .     "SW948_LARGE_INTESTINE", "SIHA_CERVIX", "T173_FIBROBLAST", 
  .     "T24_URINARY_TRACT", "T3M10_LUNG", "T3M4_PANCREAS", "T47D_BREAST", 
  .     "T84_LARGE_INTESTINE", "T98G_CENTRAL_NERVOUS_SYSTEM", "TALL1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "TC71_BONE", "TCCPAN2_PANCREAS", "TCCSUP_URINARY_TRACT", 
  .     "TE10_OESOPHAGUS", "TE11_OESOPHAGUS", "TE125T_FIBROBLAST", 
  .     "TE14_OESOPHAGUS", "TE159T_FIBROBLAST", "TE15_OESOPHAGUS", 
  .     "TE1_OESOPHAGUS", "TE441T_SOFT_TISSUE", "TE4_OESOPHAGUS", 
  .     "TE5_OESOPHAGUS", "TE617T_SOFT_TISSUE", "TE6_OESOPHAGUS", 
  .     "TE8_OESOPHAGUS", "TE9_OESOPHAGUS", "TEN_ENDOMETRIUM", "TF1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "TGBC11TKB_STOMACH", "THP1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "TIG3TD_FIBROBLAST", "TM87_SOFT_TISSUE", "TM31_CENTRAL_NERVOUS_SYSTEM", 
  .     "TO175T_FIBROBLAST", "TOLEDO_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "TOV112D_OVARY", "TOV21G_OVARY", "TT2609C02_THYROID", "TTC709_SOFT_TISSUE", 
  .     "TTC1240_SOFT_TISSUE", "TTC549_SOFT_TISSUE", "TTC642_SOFT_TISSUE", 
  .     "TT_OESOPHAGUS", "TT_THYROID", "TUHR10TKB_KIDNEY", "TUHR14TKB_KIDNEY", 
  .     "TUHR4TKB_KIDNEY", "TYKNU_OVARY", "U118MG_CENTRAL_NERVOUS_SYSTEM", 
  .     "U178_CENTRAL_NERVOUS_SYSTEM", "U251MG_CENTRAL_NERVOUS_SYSTEM", 
  .     "U266B1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "U2OS_BONE", 
  .     "U343_CENTRAL_NERVOUS_SYSTEM", "U87MG_CENTRAL_NERVOUS_SYSTEM", 
  .     "U937_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "UACC257_SKIN", 
  .     "UACC62_SKIN", "UACC812_BREAST", "UACC893_BREAST", "UBLC1_URINARY_TRACT", 
  .     "UMUC1_URINARY_TRACT", "UMUC3_URINARY_TRACT", "UO31_KIDNEY", 
  .     "UOK101_KIDNEY", "VCAP_PROSTATE", "VMCUB1_URINARY_TRACT", 
  .     "VMRCRCW_KIDNEY", "VMRCRCZ_KIDNEY", "WM115_SKIN", "WM1799_SKIN", 
  .     "WM2664_SKIN", "WM793_SKIN", "WM88_SKIN", "WM983B_SKIN", 
  .     "WSUDLCL2_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "YAPC_PANCREAS", 
  .     "YD10B_UPPER_AERODIGESTIVE_TRACT", "YD15_SALIVARY_GLAND", 
  .     "YD38_UPPER_AERODIGESTIVE_TRACT", "YD8_UPPER_AERODIGESTIVE_TRACT", 
  .     "YH13_CENTRAL_NERVOUS_SYSTEM", "YKG1_CENTRAL_NERVOUS_SYSTEM", 
  .     "ZR751_BREAST", "ZR7530_BREAST", "143B_BONE", "BIN67_OVARY", 
  .     "CHLA15_AUTONOMIC_GANGLIA", "CHLA266_SOFT_TISSUE", "COGAR359_SOFT_TISSUE", 
  .     "COGE352_BONE", "COGN278_AUTONOMIC_GANGLIA", "COGN305_AUTONOMIC_GANGLIA", 
  .     "COV504_OVARY", "CW9019_SOFT_TISSUE", "D425_CENTRAL_NERVOUS_SYSTEM", 
  .     "D458_CENTRAL_NERVOUS_SYSTEM", "DLD1_LARGE_INTESTINE", "F5_CENTRAL_NERVOUS_SYSTEM", 
  .     "JR_SOFT_TISSUE", "L82_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "MAC2A_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", "MYLA_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "PEDS005TPFAD_KIDNEY", "PEDS015T_SOFT_TISSUE", "RT11284_URINARY_TRACT", 
  .     "SMSCTR_SOFT_TISSUE", "SMZ1_HAEMATOPOIETIC_AND_LYMPHOID_TISSUE", 
  .     "SW982_SOFT_TISSUE", "SYO1_SOFT_TISSUE", "TC138_BONE", "TC205_BONE", 
  .     "UPCISCC152_UPPER_AERODIGESTIVE_TRACT", "UW228_CENTRAL_NERVOUS_SYSTEM"
  .     ), subscript_action = NULL, subscript_arg = "select_cl", 
  .     rlang = list(inherit = TRUE), call = dplyr::select(., c("Description", 
  .         select_cl))), class = c("vctrs_error_subscript_oob", 
  . "vctrs_error_subscript", "rlang_error", "error", "condition")))
28. handlers[[1L]](cnd)
29. cnd_signal(cnd)
30. signal_abort(cnd)

CCLE_exp

sum(select_cl %in% CCLE_info$cell_line)

CCLE_merge_info <- merge(CCLE_info,CCLE_drug,by.x = 'cell_line',by.y='CCLE Cell Line Name',all = F)

select_cl <- CCLE_merge_info %>% 
    filter(Target == 'EGFR') %>% 
    filter(tumor_type == 'Lung')

select_cl_name <-  select_cl%>%
    dplyr::select('cell_line') %>% 
    t() %>% c()

EGFR_drug_exp <- CCLE_exp %>% 
    dplyr::select(c('Description',select_cl_name)) %>%
    dplyr::filter(Description %in% drivers$V1) %>% 
    as.data.frame()

Warning message:
“Using an external vector in selections was deprecated in tidyselect 1.1.0.
ℹ Please use `all_of()` or `any_of()` instead.
  # Was:
  data %>% select(select_cl_name)

  # Now:
  data %>% select(all_of(select_cl_name))

See <https://tidyselect.r-lib.org/reference/faq-external-vector.html>.”

EGFR_drug_exp

#利用aggregate函数，对相同的基因名按列取平均
EGFR_drug_exp <- aggregate(.~Description,mean,data=EGFR_drug_exp)

rn <- EGFR_drug_exp$Description
EGFR_drug_exp <- EGFR_drug_exp[,2:ncol(EGFR_drug_exp)]
rownames(EGFR_drug_exp) <- rn
EGFR_drug_exp

EGFR_drug_exp <- log2(EGFR_drug_exp)

EGFR_drug_exp

EGFR_drug_exp$V1 = rownames(EGFR_drug_exp)

score_df <- merge(EGFR_drug_exp,drivers,by = 'V1',all = F)
score_df

FUN1 <- function(x){
    sum(x*score_df$weight_shap_total_mean)
    #sum(x)
}
score <- apply(score_df[,2:32],MARGIN  = 2,FUN = FUN1)

score

select_cl

drug_res <- select_cl %>% 
dplyr::select(c('cell_line',`IC50 (uM)`,`EC50 (uM)`)) %>% filter(cell_line %in% names(score))
head(drug_res)

drug_res$score = score[as.character(drug_res$cell_line)]

#cor.test(drug_res$LN_IC50,drug_res$score,alternative = 'less',method =  'pearson')
#cor.test(drug_res$LN_IC50,drug_res$score,method =  'kendall')
cor.test(drug_res$`IC50 (uM)`,drug_res$score,alternative = 'less',method =  'spearman')
cor.test(drug_res$`EC50 (uM)`,drug_res$score,alternative = 'less',method =  'spearman')

Warning message in cor.test.default(drug_res$`IC50 (uM)`, drug_res$score, alternative = "less", :
“Cannot compute exact p-value with ties”

	Spearman's rank correlation rho

data:  drug_res$`IC50 (uM)` and drug_res$score
S = 180450, p-value = 0.0003379
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.3462008

Warning message in cor.test.default(drug_res$`EC50 (uM)`, drug_res$score, alternative = "less", :
“Cannot compute exact p-value with ties”

	Spearman's rank correlation rho

data:  drug_res$`EC50 (uM)` and drug_res$score
S = 44641, p-value = 0.08214
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.1803435

score <- apply(score_df[,2:32],MARGIN  = 2,FUN = FUN5)

drug_res$score = score[as.character(drug_res$cell_line)]

#cor.test(drug_res$LN_IC50,drug_res$score,alternative = 'less',method =  'pearson')
#cor.test(drug_res$LN_IC50,drug_res$score,method =  'kendall')
cor.test(drug_res$`IC50 (uM)`,drug_res$score,alternative = 'less',method =  'spearman')
cor.test(drug_res$`EC50 (uM)`,drug_res$score,alternative = 'less',method =  'spearman')

Warning message in cor.test.default(drug_res$`IC50 (uM)`, drug_res$score, alternative = "less", :
“Cannot compute exact p-value with ties”

	Spearman's rank correlation rho

data:  drug_res$`IC50 (uM)` and drug_res$score
S = 156121, p-value = 0.05733
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.1646965

Warning message in cor.test.default(drug_res$`EC50 (uM)`, drug_res$score, alternative = "less", :
“Cannot compute exact p-value with ties”

	Spearman's rank correlation rho

data:  drug_res$`EC50 (uM)` and drug_res$score
S = 37114, p-value = 0.5567
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
0.01865623

score_df <- merge(EGFR_drug_exp,drivers_pos,by = 'V1',all = F)
score <- apply(score_df[,2:32],MARGIN  = 2,FUN = FUN1)

drug_res <- select_cl %>% 
dplyr::select(c('cell_line',`IC50 (uM)`,`EC50 (uM)`)) %>% filter(cell_line %in% names(score))
drug_res$score = score[as.character(drug_res$cell_line)]

cor.test(drug_res$`IC50 (uM)`,drug_res$score,alternative = 'less',method =  'spearman')
cor.test(drug_res$`EC50 (uM)`,drug_res$score,alternative = 'less',method =  'spearman')

Warning message in cor.test.default(drug_res$`IC50 (uM)`, drug_res$score, alternative = "less", :
“Cannot compute exact p-value with ties”

	Spearman's rank correlation rho

data:  drug_res$`IC50 (uM)` and drug_res$score
S = 183277, p-value = 0.0001464
alternative hypothesis: true rho is less than 0
sample estimates:
     rho 
-0.36729

Warning message in cor.test.default(drug_res$`EC50 (uM)`, drug_res$score, alternative = "less", :
“Cannot compute exact p-value with ties”

	Spearman's rank correlation rho

data:  drug_res$`EC50 (uM)` and drug_res$score
S = 42137, p-value = 0.1906
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.1141338

score_df <- merge(EGFR_drug_exp,drivers_neg,by = 'V1',all = F)
score <- apply(score_df[,2:32],MARGIN  = 2,FUN = FUN1)

drug_res <- select_cl %>% 
dplyr::select(c('cell_line',`IC50 (uM)`,`EC50 (uM)`)) %>% filter(cell_line %in% names(score))
drug_res$score = score[as.character(drug_res$cell_line)]

cor.test(drug_res$`IC50 (uM)`,drug_res$score,alternative = 'less',method =  'spearman')
cor.test(drug_res$`EC50 (uM)`,drug_res$score,alternative = 'less',method =  'spearman')

Warning message in cor.test.default(drug_res$`IC50 (uM)`, drug_res$score, alternative = "less", :
“Cannot compute exact p-value with ties”

	Spearman's rank correlation rho

data:  drug_res$`IC50 (uM)` and drug_res$score
S = 178481, p-value = 0.0005852
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.3315071

Warning message in cor.test.default(drug_res$`EC50 (uM)`, drug_res$score, alternative = "less", :
“Cannot compute exact p-value with ties”

	Spearman's rank correlation rho

data:  drug_res$`EC50 (uM)` and drug_res$score
S = 48171, p-value = 0.0164
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.2737041

read_dir <- file.path('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/output_new/')
run_name <- 'main_PC9_LUNG_run10_t0_sen_res'
#GDSC
test_drug <- 'Osimertinib'
cancer_type <- 'LUAD'
#CCLE
CCLE_Target <- 'EGFR'
CCLE_tumor_type <- 'Lung'
#gene <- 'SLC1A5'

read_dir <- file.path(read_dir,run_name)
drivers <- fread(file.path(read_dir,'driver_summary_shap_total.csv'))

drivers$rank_shap_weight = rank(-drivers$weight_shap_total_mean)
drivers$rank_grad_weight = rank(-abs(drivers$weight_grad_total_dir_mean))

drivers$directions = drivers$weight_grad_total_dir_mean >= 0
drivers$directions_cal = as.numeric(drivers$directions)
drivers[!drivers$directions,]$directions_cal = -1

GDSC_exp <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/GDSC/Cell_line_RMA_proc_basalExp.txt')
GDSC_compounds <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/GDSC/screened_compounds_rel_8.5.csv')
GDSC_cellline <- openxlsx::read.xlsx('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/GDSC/Cell_Lines_Details.xlsx')
GDSC_drug1 <- openxlsx::read.xlsx('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/GDSC/GDSC1_fitted_dose_response_27Oct23.xlsx')
GDSC_drug2 <- openxlsx::read.xlsx('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/GDSC/GDSC2_fitted_dose_response_27Oct23.xlsx')
GDSC_drug <- rbind(GDSC_drug1,GDSC_drug2)

GDSC_select <- GDSC_drug %>% dplyr::filter(GDSC_drug$COSMIC_ID %in% substring(colnames(GDSC_exp),6)) %>%
    dplyr::filter(DRUG_NAME == test_drug) %>%
    dplyr::filter(TCGA_DESC == cancer_type) 

#GDSC_select

GDSC_select_exp <- GDSC_exp %>% dplyr::select(c(1,which(substring(colnames(GDSC_exp),6) %in% GDSC_select$COSMIC_ID)))

CCLE_exp <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/CCLE/CCLE_DepMap_18Q1_RNAseq_RPKM_20180214.gct')
CCLE_info <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/CCLE/sample_info.csv')
CCLE_drug <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/CCLE/CCLE_NP24.2009_Drug_data_2015.02.24.csv')
CCLE_drug_info <- readxl::read_excel('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/CCLE/CCLE_GNF_data_090613.xls')

#利用aggregate函数，对相同的基因名按列取平均
#CCLE_exp <- aggregate(.~Description,mean,data=CCLE_exp)

CCLE_merge_info <- merge(CCLE_info,CCLE_drug,by.x = 'cell_line',by.y='CCLE Cell Line Name',all = F)

CCLE_select <- CCLE_merge_info %>% 
    filter(Target == CCLE_Target) %>% 
    filter(tumor_type == CCLE_tumor_type)

CCLE_select_name <-  CCLE_select%>%
    dplyr::select('cell_line') %>% 
    t() %>% c()

CCLE_drug_exp <- CCLE_exp %>% 
    dplyr::select(c('Description',CCLE_select_name)) %>%
    dplyr::filter(Description %in% drivers$V1) %>% 
    as.data.frame()

pvalue_list <- c()
corr_list <- c()
gene_list <- drivers$V1[drivers$V1 %in% GDSC_exp$GENE_SYMBOLS]
for ( gene in gene_list){
    message(gene)
    GDSC_single_gene <-  GDSC_select_exp%>% dplyr::filter(GENE_SYMBOLS == gene) %>% t() %>% as.data.frame()
    GDSC_single_gene <- GDSC_single_gene %>% mutate(COSMIC_ID = substring(rownames(GDSC_single_gene),6))
    GDSC_single_gene <- GDSC_single_gene[2:nrow(GDSC_single_gene),] %>% apply(2,as.numeric)
    colnames(GDSC_single_gene) <- c('gene','COSMIC_ID') 
    GDSC_single_gene <- GDSC_single_gene %>% as.data.frame()
    GDSC_single_gene$group <- GDSC_single_gene$gene >= mean(GDSC_single_gene$gene) %>% as.numeric()

    cor_df <- GDSC_select %>% 
    dplyr::select(c('COSMIC_ID','LN_IC50','AUC')) %>% 
    merge(GDSC_single_gene,by = 'COSMIC_ID',all = T)


    pvalue_list <- cor.test(cor_df$LN_IC50,cor_df$gene,alternative = 'two.sided',method =  'pearson')[[3]] %>% c(pvalue_list,.)
    corr_list <- cor.test(cor_df$LN_IC50,cor_df$gene,alternative = 'two.sided',method =  'pearson')[[4]] %>% c(corr_list,.)
}

gene_cor_plot_df <- data.frame(gene = gene_list,pvalue= pvalue_list,corr = corr_list)

GTF2B

MSH6

TFDP1

MYO1B

TUBA1B

SLC1A5

TGM2

BARD1

TUBB4B

RRBP1

ANXA2

PLK2

PSMC4

DGKE

CEBPD

HSPA2

RAB31

TFAP2C

CD9

TPM1

LMO7

KLF5

TRIB1

HIST1H1C

DAAM1

pvalue_list <- c()
corr_list <- c()
gene_list <- drivers$V1[drivers$V1 %in% GDSC_exp$GENE_SYMBOLS]
for ( gene in gene_list){
    message(gene)
    GDSC_single_gene <-  GDSC_select_exp%>% dplyr::filter(GENE_SYMBOLS == gene) %>% t() %>% as.data.frame()
    GDSC_single_gene <- GDSC_single_gene %>% mutate(COSMIC_ID = substring(rownames(GDSC_single_gene),6))
    GDSC_single_gene <- GDSC_single_gene[2:nrow(GDSC_single_gene),] %>% apply(2,as.numeric)
    colnames(GDSC_single_gene) <- c('gene','COSMIC_ID') 
    GDSC_single_gene <- GDSC_single_gene %>% as.data.frame()
    GDSC_single_gene$group <- GDSC_single_gene$gene >= mean(GDSC_single_gene$gene) %>% as.numeric()

    cor_df <- GDSC_select %>% 
    dplyr::select(c('COSMIC_ID','LN_IC50','AUC')) %>% 
    merge(GDSC_single_gene,by = 'COSMIC_ID',all = T)


    pvalue_list <- cor.test(cor_df$AUC,cor_df$gene,alternative = 'two.sided',method =  'pearson')[[3]] %>% c(pvalue_list,.)
    corr_list <- cor.test(cor_df$AUC,cor_df$gene,alternative = 'two.sided',method =  'pearson')[[4]] %>% c(corr_list,.)
}

gene_cor_plot_df_auc <- data.frame(gene = gene_list,pvalue= pvalue_list,corr = corr_list)

GTF2B

MSH6

TFDP1

MYO1B

TUBA1B

SLC1A5

TGM2

BARD1

TUBB4B

RRBP1

ANXA2

PLK2

PSMC4

DGKE

CEBPD

HSPA2

RAB31

TFAP2C

CD9

TPM1

LMO7

KLF5

TRIB1

HIST1H1C

DAAM1

gene_cor_plot_df$with = 'IC50'
gene_cor_plot_df_auc$with = 'AUC'
gene_cor_plot_df <- rbind(gene_cor_plot_df,gene_cor_plot_df_auc)

gene_cor_plot_df$p_status <- gene_cor_plot_df$pvalue <= 0.05

gene_cor_plot_df

p1 <- ggplot(data = gene_cor_plot_df)+
    geom_point(aes(x = with,y = gene,size=abs(corr),color = p_status))+
    geom_text(aes(x = with,y = gene,label = round(corr,2)),color = 'white')+
    scale_size_continuous(range = c(8, 15))+
    scale_colour_manual(values = c('TRUE'= "#8C0303", 'FALSE' = "#2A398C"))+
    theme_bw()
p1

ggsave(p1,filename = paste0(run_name,'_',test_drug,'_',cancer_type,'_genecor_with_drug.pdf'),height = 10,width =5)

rn <- CCLE_drug_exp$Description
CCLE_drug_exp <- CCLE_drug_exp[,2:ncol(CCLE_drug_exp)]
rownames(CCLE_drug_exp) <- rn
CCLE_drug_exp <- log2(CCLE_drug_exp)
CCLE_drug_exp$GENE_SYMBOLS = rownames(CCLE_drug_exp)

table(CCLE_select$Compound)

Erlotinib Lapatinib   ZD-6474 
       31        31        31

CCLE_surv <-  CCLE_select %>% filter(Compound == 'Erlotinib') %>%
dplyr::select(c('cell_line',`IC50 (uM)`,`EC50 (uM)`))

gene = 'GTF2B'
cor_df <- CCLE_drug_exp %>% dplyr::filter(GENE_SYMBOLS == gene) %>% t() %>% as.data.frame()%>% 
mutate(cell_line = colnames(CCLE_drug_exp)) %>%
mutate(exp = as.numeric(CCLE_drug_exp[gene,])) %>%
dplyr::select(c('exp','cell_line')) %>%
merge(y =CCLE_surv,by = 'cell_line',all = F)
#GDSC_single_gene <- GDSC_single_gene[2:nrow(GDSC_single_gene),] %>% apply(2,as.numeric)
#colnames(GDSC_single_gene) <- c('gene','COSMIC_ID') 
#GDSC_single_gene <- GDSC_single_gene %>% as.data.frame()
pvalue_list <- cor.test(cor_df$`IC50 (uM)`,cor_df$exp,alternative = 'two.sided',method =  'pearson')[[3]] 
corr_list <- cor.test(cor_df$`EC50 (uM)`,cor_df$exp,alternative = 'two.sided',method =  'pearson')[[4]] 
pvalue_list
corr_list

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”

pvalue_list <- c()
corr_list <- c()
gene_list <- drivers$V1[drivers$V1 %in% CCLE_drug_exp$GENE_SYMBOLS]

CCLE_surv <-  CCLE_select %>% filter(Compound == 'Erlotinib') %>%
dplyr::select(c('cell_line',`IC50 (uM)`,`EC50 (uM)`))

for ( gene in gene_list){
    message(gene)
    cor_df <- CCLE_drug_exp %>% dplyr::filter(GENE_SYMBOLS == gene) %>% t() %>% as.data.frame()%>% 
                mutate(cell_line = colnames(CCLE_drug_exp)) %>%
                mutate(exp = as.numeric(CCLE_drug_exp[gene,])) %>%
                dplyr::select(c('exp','cell_line')) %>%
                merge(y =CCLE_surv,by = 'cell_line',all = F)


    pvalue_list <- cor.test(cor_df$`IC50 (uM)`,cor_df$exp,alternative = 'two.sided',method =  'pearson')[[3]] %>% c(pvalue_list,.)
    corr_list <- cor.test(cor_df$`IC50 (uM)`,cor_df$exp,alternative = 'two.sided',method =  'pearson')[[4]] %>% c(corr_list,.)
}

cor_plot_df_ic50 <- data.frame(gene = gene_list,pvalue= pvalue_list,corr = corr_list)

GTF2B

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
MSH6

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TFDP1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
MYO1B

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TUBA1B

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
SLC1A5

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TGM2

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
BARD1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TUBB4B

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
RRBP1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
ANXA2

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
PLK2

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
PSMC4

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
DGKE

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
CEBPD

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
HSPA2

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
RAB31

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TFAP2C

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
CD9

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TPM1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
LMO7

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
KLF5

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TRIB1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
HIST1H1C

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
DAAM1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”

cor_plot_df_ic50

pvalue_list <- c()
corr_list <- c()
gene_list <- drivers$V1[drivers$V1 %in% CCLE_drug_exp$GENE_SYMBOLS]

CCLE_surv <-  CCLE_select %>% filter(Compound == 'Lapatinib') %>%
dplyr::select(c('cell_line',`IC50 (uM)`,`EC50 (uM)`))

for ( gene in gene_list){
    message(gene)
    cor_df <- CCLE_drug_exp %>% dplyr::filter(GENE_SYMBOLS == gene) %>% t() %>% as.data.frame()%>% 
                mutate(cell_line = colnames(CCLE_drug_exp)) %>%
                mutate(exp = as.numeric(CCLE_drug_exp[gene,])) %>%
                dplyr::select(c('exp','cell_line')) %>%
                merge(y =CCLE_surv,by = 'cell_line',all = F)


    pvalue_list <- cor.test(cor_df$`IC50 (uM)`,cor_df$exp,alternative = 'two.sided',method =  'pearson')[[3]] %>% c(pvalue_list,.)
    corr_list <- cor.test(cor_df$`IC50 (uM)`,cor_df$exp,alternative = 'two.sided',method =  'pearson')[[4]] %>% c(corr_list,.)
}

cor_plot_df_ic50_2 <- data.frame(gene = gene_list,pvalue= pvalue_list,corr = corr_list)

GTF2B

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
MSH6

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TFDP1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
MYO1B

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TUBA1B

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
SLC1A5

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TGM2

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
BARD1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TUBB4B

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
RRBP1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
ANXA2

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
PLK2

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
PSMC4

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
DGKE

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
CEBPD

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
HSPA2

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
RAB31

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TFAP2C

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
CD9

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TPM1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
LMO7

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
KLF5

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TRIB1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
HIST1H1C

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
DAAM1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”

pvalue_list <- c()
corr_list <- c()
gene_list <- drivers$V1[drivers$V1 %in% CCLE_drug_exp$GENE_SYMBOLS]

CCLE_surv <-  CCLE_select %>% filter(Compound == 'ZD-6474') %>%
dplyr::select(c('cell_line',`IC50 (uM)`,`EC50 (uM)`))

for ( gene in gene_list){
    message(gene)
    cor_df <- CCLE_drug_exp %>% dplyr::filter(GENE_SYMBOLS == gene) %>% t() %>% as.data.frame()%>% 
                mutate(cell_line = colnames(CCLE_drug_exp)) %>%
                mutate(exp = as.numeric(CCLE_drug_exp[gene,])) %>%
                dplyr::select(c('exp','cell_line')) %>%
                merge(y =CCLE_surv,by = 'cell_line',all = F)


    pvalue_list <- cor.test(cor_df$`IC50 (uM)`,cor_df$exp,alternative = 'two.sided',method =  'pearson')[[3]] %>% c(pvalue_list,.)
    corr_list <- cor.test(cor_df$`IC50 (uM)`,cor_df$exp,alternative = 'two.sided',method =  'pearson')[[4]] %>% c(corr_list,.)
}

cor_plot_df_ic50_3 <- data.frame(gene = gene_list,pvalue= pvalue_list,corr = corr_list)

GTF2B

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
MSH6

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TFDP1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
MYO1B

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TUBA1B

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
SLC1A5

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TGM2

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
BARD1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TUBB4B

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
RRBP1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
ANXA2

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
PLK2

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
PSMC4

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
DGKE

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
CEBPD

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
HSPA2

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
RAB31

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TFAP2C

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
CD9

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TPM1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
LMO7

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
KLF5

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
TRIB1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
HIST1H1C

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”
DAAM1

Warning message:
“There was 1 warning in `mutate()`.
ℹ In argument: `exp = as.numeric(CCLE_drug_exp[gene, ])`.
Caused by warning:
! NAs introduced by coercion”

cor_plot_df_ic50$with = 'Erlotinib'
cor_plot_df_ic50_2$with = 'Lapatinib'
cor_plot_df_ic50_3$with = 'ZD-6474'
cor_plot_df <- rbind(cor_plot_df_ic50,cor_plot_df_ic50_2,cor_plot_df_ic50_3)

cor_plot_df

cor_plot_df$p_status <- cor_plot_df$pvalue <= 0.05

p2 <- ggplot(data = cor_plot_df)+
    geom_point(aes(x = with,y = gene,size=abs(corr),color = p_status))+
    geom_text(aes(x = with,y = gene,label = round(corr,2)),color = 'white')+
    scale_size_continuous(range = c(8, 15))+
    scale_colour_manual(values = c('TRUE'= "#8C0303", 'FALSE' = "#2A398C"))+
    theme_bw()
p2

gene_cor_plot_df <- gene_cor_plot_df %>% filter(with == 'IC50')
gene_cor_plot_df$with = 'Osimertinib'
gene_cor_plot_df <- rbind(cor_plot_df,gene_cor_plot_df)

p3 <- ggplot(data = gene_cor_plot_df)+
    geom_point(aes(x = with,y = gene,size=abs(corr),color = p_status))+
    geom_text(aes(x = with,y = gene,label = round(corr,2)),color = 'white')+
    scale_size_continuous(range = c(8, 15))+
    scale_colour_manual(values = c('TRUE'= "#8C0303", 'FALSE' = "#2A398C"))+
    theme_bw()
p3

table(gene_cor_plot_df$gene)
table(gene_cor_plot_df$with)

   ANXA2    BARD1      CD9    CEBPD    DAAM1     DGKE    GTF2B HIST1H1C 
       4        4        4        4        4        4        4        4 
   HSPA2     KLF5     LMO7     MSH6    MYO1B     PLK2    PSMC4    RAB31 
       4        4        4        4        4        4        4        4 
   RRBP1   SLC1A5   TFAP2C    TFDP1     TGM2     TPM1    TRIB1   TUBA1B 
       4        4        4        4        4        4        4        4 
  TUBB4B 
       4

  Erlotinib   Lapatinib Osimertinib     ZD-6474 
         25          25          25          25

gene_cor_plot_mtx <-  gene_cor_plot_df %>% dplyr::select(c('gene','corr','with')) %>%  tidyr::spread(key = 'with',value = 'corr')
rownames(gene_cor_plot_mtx) <- gene_cor_plot_mtx$gene
gene_cor_plot_mtx <- gene_cor_plot_mtx[,2:ncol(gene_cor_plot_mtx)] %>% as.matrix()

gene_cor_plot_mtx

gene_cor_p_mtx <-  gene_cor_plot_df %>% dplyr::select(c('gene','pvalue','with')) %>%  tidyr::spread(key = 'with',value = 'pvalue')
rownames(gene_cor_p_mtx) <- gene_cor_p_mtx$gene
gene_cor_p_mtx <- gene_cor_p_mtx[,2:ncol(gene_cor_p_mtx)] %>% as.matrix()

gene_cor_p_mtx

library(ComplexHeatmap)
library(circlize)
col_fun = colorRamp2(c(-0.25,0,0.25),c('#D28130','white','#559073'))
cell_fun = function(j, i, x, y, width, height, fill) {
        if (gene_cor_p_mtx[i,j] <=0.05){
            grid.text(sprintf("%.3f", gene_cor_plot_mtx[i, j]), x, y, gp = gpar(fontsize = 10,col = '#A11715', fontface = "bold"))
        }else{
            grid.text(sprintf("%.3f", gene_cor_plot_mtx[i, j]), x, y, gp = gpar(fontsize = 10,col = 'black'))
        }
}

p <- Heatmap(gene_cor_plot_mtx,
        cluster_rows = T,
        #clustering_distance_rows = "pearson",
        show_row_dend =F,
        cluster_columns = T,
        row_names_side = "left",
        show_column_dend  =F,
        row_names_gp = gpar(fontsize = 10),
        column_names_gp = gpar(fontsize = 10),
        col = col_fun,
        cell_fun = cell_fun,
        rect_gp = gpar(col = "white", lwd = 2),
        column_title  = 'Drugs target EGFR',
        column_title_gp = gpar(fontsize = 20, fontface = "bold"),
        row_title = "Driver genes", row_title_rot = 90,
        row_title_gp = gpar(fontsize = 20, fontface = "bold"),)
p

pdf(file = "/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/sen_res_EGFR_drugs_heatmap.pdf",width = 8/1.5,height = 12/1.5)
p
dev.off()

tgene_cor_p_mtx <- t(gene_cor_p_mtx)
tgene_cor_plot_mtx <- t(gene_cor_plot_mtx)

drivers <- drivers %>% as.data.frame()
rownames(drivers) <- drivers$V1
directions_cal <- drivers%>% dplyr::select('directions_cal')

weight_cal <- drivers%>% dplyr::select('weight_shap_total_mean') %>% normalize()

col_fun = colorRamp2(c(-0.25,0,0.25),c('#D28130','white','#559073'))
cell_fun = function(j, i, x, y, width, height, fill) {
        if (tgene_cor_p_mtx[i,j] <=0.05){
            grid.text(sprintf("%.3f", tgene_cor_plot_mtx[i, j]), x, y, gp = gpar(fontsize = 10,col = '#A11715', fontface = "bold"))
        }else{
            grid.text(sprintf("%.3f", tgene_cor_plot_mtx[i, j]), x, y, gp = gpar(fontsize = 10,col = 'black'))
        }
}
col = list(Direction = c("-1" = "#FF09A4", "1" = "#32510A"))
#library(circlize)
#col_fun2 = colorRamp2(c(-2, -1, 0,1), c("#A6335D", "#ED6193", "#C6C6C6","#91374B"))
ha = HeatmapAnnotation(Direction = as.character(directions_cal[colnames(tgene_cor_plot_mtx),]),
                       `Normalized SHAP weight` = anno_barplot(weight_cal[colnames(tgene_cor_plot_mtx),],gp = gpar(fill ='#779CD2') ),
                       col = col,
                       gp = gpar(col = "white",lty=1,
                                lwd = 6),
                       height = unit(25, "mm"),
                       gap = unit(c(1.5), "mm"))

p <- Heatmap(tgene_cor_plot_mtx,
        cluster_rows = T,
        #clustering_distance_rows = "pearson",
        show_row_dend =F,
        cluster_columns = T,
        row_names_side = "left",
        show_column_dend  =F,
        row_names_gp = gpar(fontsize = 10),
        column_names_gp = gpar(fontsize = 10),
        col = col_fun,
        cell_fun = cell_fun,
        rect_gp = gpar(col = "white", lwd = 2),
        column_title  = 'Drugs target EGFR',
        column_title_gp = gpar(fontsize = 20, fontface = "bold"),
        row_title = "Driver genes", row_title_rot = 90,
        row_title_gp = gpar(fontsize = 20, fontface = "bold"),
        bottom_annotation = ha,)
p

pdf(file = "/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/H_sen_res_EGFR_drugs_heatmap.pdf",width = 21/1.5,height = 7/1.5)
p
dev.off()

FUN1 <- function(x){
    sum(x*score_df$weight_shap_total_mean)
    #sum(x)
}

normalize <- function(v) {
  (v - min(v)) / (max(v) - min(v))
}
FUN2 <- function(x){
    sum(x*normalize(score_df$weight_shap_total_mean))
    #sum(x)
}
FUN3 <- function(x){
    mean(x*normalize(score_df$weight_shap_total_mean))
    #sum(x)
}
FUN4 <- function(x){
    mean(x*score_df$weight_shap_total_mean)
    #sum(x)
}
FUN5 <- function(x){
    sum(x*score_df$weight_shap_total_mean*score_df$directions_cal)
    #sum(x)
}

score_df <- merge(GDSC_select_exp,drivers,by.x = 'GENE_SYMBOLS',by.y = 'V1',all = F)
score <- apply(score_df[,2:ncol(GDSC_select_exp)],MARGIN  = 2,FUN = FUN5)
names(score) <- names(score) %>% substring(.,6)
GDSC_select$score = score[as.character(GDSC_select$COSMIC_ID)]

cor.test(GDSC_select$LN_IC50,GDSC_select$score,alternative = 'less',method =  'spearman')
cor.test(GDSC_select$AUC,GDSC_select$score,alternative = 'less',method =  'spearman')

	Spearman's rank correlation rho

data:  GDSC_select$LN_IC50 and GDSC_select$score
S = 49784, p-value = 0.00666
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.3163406

	Spearman's rank correlation rho

data:  GDSC_select$AUC and GDSC_select$score
S = 48350, p-value = 0.01506
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.2784241

ggplot(data = GDSC_select,aes(x=score,y=LN_IC50))+
geom_point(size=3,shape=21,color='black',fill='#03658C')+
geom_smooth(size=1.5,method=lm , color="#BA002B", fill="#69b3a2", se=TRUE) +
geom_text(aes(x=0,y=5,label='Cor = 0.3163406  \n P-value = 0.00666'),size=4,color = '#03658C')+
xlab('Drivers causal score')+
ylab('IC50 (uM)')+
theme_classic()

Warning message:
“Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.”
Warning message in geom_text(aes(x = 0, y = 5, label = "Cor = 0.3163406  \n P-value = 0.00666"), :
“All aesthetics have length 1, but the data has 61 rows.
ℹ Did you mean to use `annotate()`?”
`geom_smooth()` using formula = 'y ~ x'

corp <- ggplot(data = GDSC_select,aes(x=score,y=LN_IC50))+
geom_point(size=10,shape=21,stork=2,color='black',fill='#559073CC')+
geom_smooth(size=3,method=lm , color="#BA002B", fill="#69b3a2", se=TRUE) +
geom_text(aes(x=-0.005,y=5,label='Cor = 0.3163406  \n P-value = 0.00666'),size=12,color = 'black')+
xlab('Drivers causal score')+
ylab('IC50 (uM)')+
theme_classic()+
#scale_color_manual(values = c('In two pathway'= '#559073FF','Out of two pathway'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=24),
    axis.title.x = element_text(vjust = -5),
    axis.title.y = element_text(vjust = 6),
   axis.text = element_text(face = 'italic',size=20,colour = 'black'),
   axis.text.x = element_text(angle = 60,vjust = 0.5),
    #axis.text.y = element_text(hjust = 8),
    axis.ticks = element_line(linewidth = 1.5),
   axis.ticks.length = unit(10,'points'),
   axis.line = element_line(linewidth = 1.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   panel.border = element_blank(),
   panel.grid = element_blank(),
   #panel.grid.major.x =element_line(),
   legend.key.size = unit(20,'points'),
   legend.text = element_text(face = 'italic',size=18),
   #legend.title = element_text(face = 'bold',size=18), 
   legend.title = element_blank(),
   legend.position = 'top'
      
)
corp

Warning message in geom_point(size = 10, shape = 21, stork = 2, color = "black", :
“Ignoring unknown parameters: `stork`”
Warning message in geom_text(aes(x = -0.005, y = 5, label = "Cor = 0.3163406  \n P-value = 0.00666"), :
“All aesthetics have length 1, but the data has 61 rows.
ℹ Did you mean to use `annotate()`?”
`geom_smooth()` using formula = 'y ~ x'

ggsave(plot = corp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/sen_res_corp.pdf',
       width =16/1.5, height =16/1.5)
ggsave(plot = corp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/sen_res_corp.png',
       width =16/1.5, height =16/1.5)

Warning message in geom_text(aes(x = -0.005, y = 5, label = "Cor = 0.3163406  \n P-value = 0.00666"), :
“All aesthetics have length 1, but the data has 61 rows.
ℹ Did you mean to use `annotate()`?”
`geom_smooth()` using formula = 'y ~ x'
Warning message in geom_text(aes(x = -0.005, y = 5, label = "Cor = 0.3163406  \n P-value = 0.00666"), :
“All aesthetics have length 1, but the data has 61 rows.
ℹ Did you mean to use `annotate()`?”
`geom_smooth()` using formula = 'y ~ x'

# 计算分位数，这里我们分为三组，所以使用0%, 33%, 67% 和 100%的分位数
quantiles <- quantile(GDSC_select$score, probs = c(0, 1/3, 2/3, 1))

# 使用cut函数将score分组，并创建新列group
GDSC_select$group <- cut(GDSC_select$score, breaks = quantiles, 
                         labels = c("Low", "Medium", "High"), include.lowest = TRUE)

GDSC_select$group <- factor(GDSC_select$group,levels = c("High","Medium","Low"))
# 查看结果
head(GDSC_select)

p <- ggplot(data = GDSC_select,aes(x=group,y=LN_IC50,color=group))+
geom_boxplot(size=1.5)+
ggbeeswarm::geom_quasirandom(method = "smiley",size=6,alpha=0.7)+

theme_classic()+#设置两轴白底主体

theme(line = element_line(size=1.5),#坐标轴除夕及文字大小
     axis.title = element_text(size=18),
     axis.text = element_text(size=14),
     axis.ticks = element_line(size=1.5),
     axis.ticks.length = unit(0.3, "cm"))+

ggsci::scale_color_npg()

p

# 比较Low组与Medium组
low_medium_t_test <- t.test(LN_IC50 ~ group, data = GDSC_select,alternative ='less', subset = group %in% c("Low", "Medium"))
print("Low vs Medium:")
print(low_medium_t_test)

# 比较Low组与High组
low_high_t_test <- t.test(LN_IC50 ~ group, data = GDSC_select,alternative ='less', subset = group %in% c("Low", "High"))
print("Low vs High:")
print(low_high_t_test)

# 比较Medium组与High组
medium_high_t_test <- t.test(LN_IC50 ~ group, data = GDSC_select,alternative ='less',  subset = group %in% c("Medium", "High"))
print("Medium vs High:")
print(medium_high_t_test)

[1] "Low vs Medium:"

	Welch Two Sample t-test

data:  LN_IC50 by group
t = -2.2825, df = 28.817, p-value = 0.01502
alternative hypothesis: true difference in means between group Medium and group Low is less than 0
95 percent confidence interval:
      -Inf -0.315564
sample estimates:
mean in group Medium    mean in group Low 
            1.084215             2.319713 

[1] "Low vs High:"

	Welch Two Sample t-test

data:  LN_IC50 by group
t = -2.4293, df = 28.482, p-value = 0.01084
alternative hypothesis: true difference in means between group High and group Low is less than 0
95 percent confidence interval:
       -Inf -0.4008829
sample estimates:
mean in group High  mean in group Low 
         0.9841209          2.3197129 

[1] "Medium vs High:"

	Welch Two Sample t-test

data:  LN_IC50 by group
t = -0.14618, df = 37.985, p-value = 0.4423
alternative hypothesis: true difference in means between group High and group Medium is less than 0
95 percent confidence interval:
     -Inf 1.054361
sample estimates:
  mean in group High mean in group Medium 
           0.9841209            1.0842150

# 比较Low组与Medium组
low_medium_t_test <- wilcox.test(LN_IC50 ~ group, data = GDSC_select,alternative ='less',  subset = group %in% c("Low", "Medium"))
print("Low vs Medium:")
print(low_medium_t_test)

# 比较Low组与High组
low_high_t_test <- wilcox.test(LN_IC50 ~ group, data = GDSC_select,alternative ='less',  subset = group %in% c("Low", "High"))
print("Low vs High:")
print(low_high_t_test)

# 比较Medium组与High组
medium_high_t_test <- wilcox.test(LN_IC50 ~ group, data = GDSC_select,alternative ='less',  subset = group %in% c("Medium", "High"))
print("Medium vs High:")
print(medium_high_t_test)

[1] "Low vs Medium:"

	Wilcoxon rank sum exact test

data:  LN_IC50 by group
W = 135, p-value = 0.02565
alternative hypothesis: true location shift is less than 0

[1] "Low vs High:"

	Wilcoxon rank sum exact test

data:  LN_IC50 by group
W = 125, p-value = 0.0132
alternative hypothesis: true location shift is less than 0

[1] "Medium vs High:"

	Wilcoxon rank sum exact test

data:  LN_IC50 by group
W = 195, p-value = 0.4521
alternative hypothesis: true location shift is less than 0

p <- ggplot(data = GDSC_select,aes(x=group,y=LN_IC50))+
geom_boxplot(aes(fill=group),size=1.5)+
#ggbeeswarm::geom_quasirandom(aes(color=group),method = "smiley",size=6,alpha=0.7)+
ggsignif::geom_signif(aes(x=group,y=LN_IC50),comparisons =  list(c('Low', "Medium"),c('Low', "High"),c('Medium', "High")),step_increase = 0.15,map_signif_level = F,test = 't.test',test.args = c('greater')) +

theme_classic()+#设置两轴白底主体

theme(line = element_line(size=1.5),#坐标轴除夕及文字大小
     axis.title = element_text(size=18),
     axis.text = element_text(size=14),
     axis.ticks = element_line(size=1.5),
     axis.ticks.length = unit(0.3, "cm"))+

#ggsci::scale_color_npg()+
ggsci::scale_fill_npg()

p

# 计算分位数，这里我们分为三组，所以使用0%, 33%, 67% 和 100%的分位数
quantiles <- quantile(GDSC_select$score, probs = c(0, 0.5, 1))

# 使用cut函数将score分组，并创建新列group
GDSC_select$group2 <- cut(GDSC_select$score, breaks = quantiles, 
                         labels = c("Low", "High"), include.lowest = TRUE)

GDSC_select$group2 <- factor(GDSC_select$group2,levels = c("High","Low"))
# 查看结果
head(GDSC_select)

p <- ggplot(data = GDSC_select,aes(x=group2,y=LN_IC50))+
geom_boxplot(aes(fill=group2),size=1.5)+
#ggbeeswarm::geom_quasirandom(aes(color=group),method = "smiley",size=6,alpha=0.7)+
ggsignif::geom_signif(aes(x=group2,y=LN_IC50),comparisons =  list(c('Low', "High")),map_signif_level = F,test = 't.test',test.args = c('greater')) +

theme_classic()+#设置两轴白底主体

theme(line = element_line(size=1.5),#坐标轴除夕及文字大小
     axis.title = element_text(size=18),
     axis.text = element_text(size=14),
     axis.ticks = element_line(size=1.5),
     axis.ticks.length = unit(0.3, "cm"))+

#ggsci::scale_color_npg()+
ggsci::scale_fill_npg()

p

score_boxp <- ggplot(data = GDSC_select,aes(x=group2,y=LN_IC50,fill=group2))+
stat_boxplot(geom = "errorbar",linewidth=1.5,width = 0.5)+
#geom_violin(outliers = F,linewidth=1.5,color='black')+
geom_boxplot(outliers = F,linewidth=1.5,color='black')+
#geom_jitter(width = 0.15,size=8,shape=21,stroke=1.5,alpha=0.8)+
#ggbeeswarm::geom_quasirandom(method = "smiley",size=8,shape=21,stroke=1.5,alpha=0.8)+
ggsignif::geom_signif(
                      comparisons =  list(c('Low', "High")),
                    step_increase = 0.15,
                    annotations= c('P-value = 0.021'),
                    textsize = 8,size=1.5,vjust=0) +

theme_classic()+
xlab('Group by CRS')+
ylab('IC50 (uM)')+
ggtitle("GDSC")+
theme_bw()+
#scale_fill_manual(values = c('T14 T0'= '#559073FF','T14 T7'='#D28130FF'))+
ggsci::scale_fill_npg()+
ggsci::scale_color_npg()+
#scale_color_manual(values = c('T14 T0'= '#559073FF','T14 T7'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5),
    axis.title.y = element_text(vjust = 6),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(angle = 60,vjust = 0.5),
    #axis.text.y = element_text(hjust = 8),
    axis.ticks = element_line(linewidth = 1.5),
   axis.ticks.length = unit(10,'points'),
   axis.line = element_line(linewidth = 1.5),
   plot.title = element_text(face = 'bold',size=28,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   panel.border = element_blank(),
   panel.grid = element_blank(),
   #panel.grid.major.x =element_line(),
   legend.key.size = unit(20,'points'),
   legend.text = element_text(face = 'italic',size=18),
   #legend.title = element_text(face = 'bold',size=18), 
   legend.title = element_blank(),
   legend.position = 'none')

score_boxp

ggsave(plot = score_boxp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/sen_res_score_boxp.pdf',
       width =14/1.5, height =14/1.5)
ggsave(plot = score_boxp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/sen_res_score_boxp.png',
       width =16/1.5, height =16/1.5)

rn <- CCLE_drug_exp$Description
CCLE_drug_exp <- CCLE_drug_exp[,2:ncol(CCLE_drug_exp)]
rownames(CCLE_drug_exp) <- rn
CCLE_drug_exp <- log2(CCLE_drug_exp)
CCLE_drug_exp$V1 = rownames(CCLE_drug_exp)

score_df <- merge(CCLE_drug_exp,drivers,by = 'V1',all = F)

score <- apply(score_df[,2:32],MARGIN  = 2,FUN = FUN1)

drug_res <- CCLE_select %>% 
dplyr::select(c('cell_line',`IC50 (uM)`,`EC50 (uM)`)) %>% filter(cell_line %in% names(score))
drug_res$score = score[as.character(drug_res$cell_line)]

cor.test(drug_res$`IC50 (uM)`,drug_res$score,alternative = 'less',method =  'spearman')
cor.test(drug_res$`EC50 (uM)`,drug_res$score,alternative = 'less',method =  'spearman')

Warning message in cor.test.default(drug_res$`IC50 (uM)`, drug_res$score, alternative = "less", :
“Cannot compute exact p-value with ties”

	Spearman's rank correlation rho

data:  drug_res$`IC50 (uM)` and drug_res$score
S = 180450, p-value = 0.0003379
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.3462008

Warning message in cor.test.default(drug_res$`EC50 (uM)`, drug_res$score, alternative = "less", :
“Cannot compute exact p-value with ties”

	Spearman's rank correlation rho

data:  drug_res$`EC50 (uM)` and drug_res$score
S = 44641, p-value = 0.08214
alternative hypothesis: true rho is less than 0
sample estimates:
       rho 
-0.1803435

ggplot(data = drug_res,aes(x=score,y=`IC50 (uM)`))+
geom_point(size=3,shape=21,color='black',fill='#03658C')+
geom_smooth(size=1.5,method=lm , color="#BA002B", fill="#69b3a2", se=TRUE) +
#geom_text(aes(x=0,y=5,label='Cor = 0.3163406  \n P-value = 0.00666'),size=4,color = '#03658C')+
xlab('Drivers causal score')+
ylab('IC50 (uM)')+
theme_classic()

Warning message:
“Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.”
`geom_smooth()` using formula = 'y ~ x'

corp <- ggplot(data = drug_res,aes(x=score,y=`IC50 (uM)`))+
geom_point(size=10,shape=21,stork=2,color='black',fill='#559073CC')+
geom_smooth(size=3,method=lm , color="#BA002B", fill="#69b3a2", se=TRUE) +
geom_text(aes(x=0.12,y=11,label='Cor = -0.3462  \n P-value = 0.0003379'),size=12,color = 'black')+
xlab('Drivers causal score')+
ylab('IC50 (uM)')+
theme_classic()+
#scale_color_manual(values = c('In two pathway'= '#559073FF','Out of two pathway'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=24),
    axis.title.x = element_text(vjust = -5),
    axis.title.y = element_text(vjust = 6),
   axis.text = element_text(face = 'italic',size=20,colour = 'black'),
   axis.text.x = element_text(angle = 60,vjust = 0.5),
    #axis.text.y = element_text(hjust = 8),
    axis.ticks = element_line(linewidth = 1.5),
   axis.ticks.length = unit(10,'points'),
   axis.line = element_line(linewidth = 1.5),
   plot.title = element_text(face = 'bold',size=24,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   panel.border = element_blank(),
   panel.grid = element_blank(),
   #panel.grid.major.x =element_line(),
   legend.key.size = unit(20,'points'),
   legend.text = element_text(face = 'italic',size=18),
   #legend.title = element_text(face = 'bold',size=18), 
   legend.title = element_blank(),
   legend.position = 'top'
      
)
corp

Warning message in geom_point(size = 10, shape = 21, stork = 2, color = "black", :
“Ignoring unknown parameters: `stork`”
Warning message in geom_text(aes(x = 0.12, y = 11, label = "Cor = -0.3462  \n P-value = 0.0003379"), :
“All aesthetics have length 1, but the data has 93 rows.
ℹ Did you mean to use `annotate()`?”
`geom_smooth()` using formula = 'y ~ x'

ggsave(plot = corp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/sen_res_corpCCLE.pdf',
       width =16/1.5, height =16/1.5)
ggsave(plot = corp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/sen_res_corpCCLE.png',
       width =16/1.5, height =16/1.5)

Warning message in geom_text(aes(x = 0.12, y = 11, label = "Cor = -0.3462  \n P-value = 0.0003379"), :
“All aesthetics have length 1, but the data has 93 rows.
ℹ Did you mean to use `annotate()`?”
`geom_smooth()` using formula = 'y ~ x'
Warning message in geom_text(aes(x = 0.12, y = 11, label = "Cor = -0.3462  \n P-value = 0.0003379"), :
“All aesthetics have length 1, but the data has 93 rows.
ℹ Did you mean to use `annotate()`?”
`geom_smooth()` using formula = 'y ~ x'

# 计算分位数，这里我们分为三组，所以使用0%, 33%, 67% 和 100%的分位数
#quantiles <- quantile(drug_res$score, probs = c(0, 1/3, 2/3, 1))

# 使用cut函数将score分组，并创建新列group
drug_res$group <- cut(drug_res$`IC50 (uM)`, breaks = c(-Inf,8,Inf), 
                         labels = c("Sensitive", "Resistance"), include.lowest = TRUE,right=FALSE)

drug_res$group <- factor(drug_res$group,levels = c("Resistance","Sensitive"))
# 查看结果
head(drug_res)

p <- ggplot(data = drug_res,aes(x=group,y=score))+
geom_boxplot(aes(fill=group),size=1.5)+
#ggbeeswarm::geom_quasirandom(aes(color=group),method = "smiley",size=6,alpha=0.7)+
ggsignif::geom_signif(aes(x=group,y=score),comparisons =  list(c('Sensitive', "Resistance")),map_signif_level = F,test = 't.test',test.args = c('greater')) +

theme_classic()+#设置两轴白底主体

theme(line = element_line(size=1.5),#坐标轴除夕及文字大小
     axis.title = element_text(size=18),
     axis.text = element_text(size=14),
     axis.ticks = element_line(size=1.5),
     axis.ticks.length = unit(0.3, "cm"))+

#ggsci::scale_color_npg()+
ggsci::scale_fill_npg()

p

response_boxp <- ggplot(data = drug_res,aes(x=group,y=score,fill=group))+
stat_boxplot(geom = "errorbar",linewidth=1.5,width = 0.5)+
#geom_violin(outliers = F,linewidth=1.5,color='black')+
geom_boxplot(outliers = F,linewidth=1.5,color='black')+
#geom_jitter(width = 0.15,size=8,shape=21,stroke=1.5,alpha=0.8)+
#ggbeeswarm::geom_quasirandom(method = "smiley",size=8,shape=21,stroke=1.5,alpha=0.8)+
ggsignif::geom_signif(
                      comparisons =  list(c('Sensitive', "Resistance")),
                    step_increase = 0.15,
                    annotations= c('P-value = 5.1e-05'),
                    textsize = 8,size=1.5,vjust=0) +

theme_classic()+
xlab('Drug response')+
ylab('CRS')+
ggtitle("CCLE")+
theme_bw()+
#scale_fill_manual(values = c('T14 T0'= '#559073FF','T14 T7'='#D28130FF'))+
ggsci::scale_fill_npg()+
ggsci::scale_color_npg()+
#scale_color_manual(values = c('T14 T0'= '#559073FF','T14 T7'='#D28130FF'))+
theme(axis.title = element_text(face = 'bold',size=20),
    axis.title.x = element_text(vjust = -5),
    axis.title.y = element_text(vjust = 6),
   axis.text = element_text(face = 'italic',size=18,colour = 'black'),
   axis.text.x = element_text(angle = 0,vjust = 0.5),
    #axis.text.y = element_text(hjust = 8),
    axis.ticks = element_line(linewidth = 1.5),
   axis.ticks.length = unit(10,'points'),
   axis.line = element_line(linewidth = 1.5),
   plot.title = element_text(face = 'bold',size=28,hjust = 0.5,vjust = 8),
   plot.margin = margin(50,50,50,50),
   panel.border = element_blank(),
   panel.grid = element_blank(),
   #panel.grid.major.x =element_line(),
   legend.key.size = unit(20,'points'),
   legend.text = element_text(face = 'italic',size=18),
   #legend.title = element_text(face = 'bold',size=18), 
   legend.title = element_blank(),
   legend.position = 'none')

response_boxp

ggsave(plot = response_boxp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/sen_res_response_boxp.pdf',
       width =14/1.5, height =14/1.5)
ggsave(plot = response_boxp,filename = '/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/sen_res_response_boxp.png',
       width =16/1.5, height =16/1.5)

drug_res

chord_data <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/res_orgin_state_transition_adata_meta.csv')

chord_data <- chord_data %>% dplyr::select(c('condition','metacell_label2'))

# Transform input data in a adjacency matrix
adjacencyData <- with(chord_data, table(condition, metacell_label2))

adjacencyData

                           metacell_label2
condition                   0 in 0 0 in 1 1 in 0 1 in 1 2 in 0 2 in 1 3 in 0
  Resistance cells in time0      0   2655      0    616      0    297      0
  Sensitive cells in time0     740      0    262      0     48      0     43
                           metacell_label2
condition                   3 in 1 4 in 1 5 in 1
  Resistance cells in time0    213    194     19
  Sensitive cells in time0       0      0      0

max(nchar(unlist(chord_data$metacell_label2)))

dim(adjacencyData)

grid.col <-c( brewer.pal(8, "Set2"),brewer.pal(4, "Set3"))
grid.col

#https://www.jianshu.com/p/73c246b87d82
#circos.clear()#for Error: Since parameter has length larger than 1, it should have same length as the number of sectors.gap.degree
chordDiagram(
  adjacencyData,  grid.col = grid.col, 
  annotationTrack = c("grid"), 
  preAllocateTracks = list(
    track.height = max(strwidth(chord_data$metacell_label2))
  )
)
circos.track(
  track.index = 1, panel.fun = function(x, y) {
    sector.name = get.cell.meta.data("sector.index")
    if (nchar(sector.name) > max(nchar(unlist(chord_data$metacell_label2)))){
        message(sector.name)
        circos.text(
          CELL_META$xcenter, CELL_META$ylim[1], 
          CELL_META$sector.index,  facing = "inside", 
          niceFacing = TRUE, adj = c(0.5, 0)
        )
    }else{
    circos.text(
      CELL_META$xcenter, CELL_META$ylim[1], 
      CELL_META$sector.index,  facing = "clockwise", 
      niceFacing = TRUE, adj = c(0, 0.5)
    )
    }
  }, bg.border = NA
)

Resistance cells in time0

Sensitive cells in time0

pdf('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/res_orgin_state_transition_adata_meta.pdf')
chordDiagram(
  adjacencyData,  grid.col = grid.col, 
  annotationTrack = c("grid"), 
  preAllocateTracks = list(
    track.height = max(strwidth(chord_data$metacell_label2))
  )
)
circos.track(
  track.index = 1, panel.fun = function(x, y) {
    sector.name = get.cell.meta.data("sector.index")
    if (nchar(sector.name) > max(nchar(unlist(chord_data$metacell_label2)))){
        message(sector.name)
        circos.text(
          CELL_META$xcenter, CELL_META$ylim[1], 
          CELL_META$sector.index,  facing = "inside", 
          niceFacing = TRUE, adj = c(0.5, 0)
        )
    }else{
    circos.text(
      CELL_META$xcenter, CELL_META$ylim[1], 
      CELL_META$sector.index,  facing = "clockwise", 
      niceFacing = TRUE, adj = c(0, 0.5)
    )
    }
  }, bg.border = NA
)
dev.off()

Resistance cells in time0

Sensitive cells in time0

probeMap <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/TCGA/LUSC/gencode.v22.annotation.gene.probeMap')
GDC_phenotype <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/TCGA/LUSC/TCGA-LUSC.GDC_phenotype.tsv')
htseq_counts <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/TCGA/LUSC/TCGA-LUSC.htseq_counts.tsv')
survival <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/TCGA/LUSC/TCGA-LUSC.survival.tsv')

ann_htseq_counts <- merge(htseq_counts,probeMap,by.x = 'Ensembl_ID',by.y = 'id',all = F)

ann_htseq_counts <- ann_htseq_counts %>% as.data.frame()

ann_htseq_counts <- ann_htseq_counts[,c('gene',colnames(htseq_counts)[2:ncol(htseq_counts)])]

#ann_htseq_counts <- aggregate(.~gene,mean,data=ann_htseq_counts)

drivers$V1

score_df <- ann_htseq_counts %>% dplyr::filter(gene %in% drivers$V1) %>% merge(y=drivers,by.x = 'gene',by.y = 'V1',all = F)

score <- apply(score_df[,2:ncol(ann_htseq_counts)],MARGIN  = 2,FUN = FUN5)

score

survival <- survival[match(names(score),survival$sample),]
survival$score <- score

survival <- survival %>% na.omit()

median(score)

survival$group<- ifelse((survival$score < median(score)), 1,2)

survival

library(survival)

fit.surv <-Surv(survival$OS.time,survival$OS)

km<-survfit(fit.surv~1,data = survival)
km_2<- survfit(fit.surv~group,data=survival)

library(survminer)

Loading required package: ggpubr


Attaching package: ‘survminer’


The following object is masked from ‘package:survival’:

    myeloma

ggsurvplot (km)

ggsurvplot(km_2)

p <- ggsurvplot(km_2, main = "Survival curve",
           conf.int = TRUE,# 可信区间
           palette = "npg",# 支持ggsci配色，自定义颜色，brewer palettes中的配色，等
           ggtheme = theme_classic(), # 支持ggplot2及其扩展包的主题
           legend.title = "Score",#改变图例名称
           legend.labs = c("Low", "High"),
           risk.table = TRUE,        # 增加risk table
           risk.table.title = "Risk set sizes",
           ncensor.plot = TRUE, #增加删失事件表
           surv.median.line = "hv",
           pval=TRUE,  #添加P值
           log.rank.weights = "1", #pval.method
)
p

Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”
Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”
Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”
Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”

#https://github.com/kassambara/survminer/issues/152

# add method to grid.draw
grid.draw.ggsurvplot <- function(x){
  survminer:::print.ggsurvplot(x, newpage = FALSE)
}
# Remember to pass object `p`.
ggsave(
  filename =paste0('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/survplot_TCGA_LUSC_byScore.pdf'),
  plot = p,
  device = 'pdf',
  #path = 'data/output',
  width = 8,
  height = 9
)

Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”
Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”
Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”

probeMap <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/TCGA/LUNG/probeMap_hugo_gencode_good_hg19_V24lift37_probemap')
GDC_phenotype <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/TCGA/LUNG/TCGA.LUNG.sampleMap_LUNG_clinicalMatrix')
htseq_counts <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/TCGA/LUNG/TCGA.LUNG.sampleMap_HiSeqV2_PANCAN')
survival <- fread('/sibcb1/chenluonanlab8/miaoyuanxiang/CauFinder-master/cycleCancer_net/TCGA/LUNG/survival_LUNG_survival.txt')

htseq_counts

drivers$V1

score_df <- htseq_counts %>% dplyr::filter(gene %in% drivers$V1) %>% merge(y=drivers,by.x = 'sample',by.y = 'V1',all = F)
score <- apply(score_df[,2:ncol(htseq_counts)],MARGIN  = 2,FUN = FUN1)

score

survival

survival <- survival[match(names(score),survival$sample),]
survival$score <- score

survival

median(score)
mean(score)

survival$group<- ifelse((survival$score < 0.015), 1,2)

table(survival$group)

  1   2 
710 419

fit.surv <-Surv(survival$OS.time,survival$OS)
km<-survfit(fit.surv~1,data = survival)
km_2<- survfit(fit.surv~group,data=survival)

ggsurvplot (km)

ggsurvplot(km_2,pval=TRUE)

fit.surv <-Surv(survival$DFI.time,survival$DFI)
km_2<- survfit(fit.surv~group,data=survival)

ggsurvplot(km_2,pval=TRUE)

fit.surv <-Surv(survival$PFI.time,survival$PFI)
km_2<- survfit(fit.surv~group,data=survival)

ggsurvplot(km_2,pval=TRUE)

survival$group<- ifelse((survival$score < 0.021), 1,2)

fit.surv <-Surv(survival$PFI.time,survival$PFI)
km_2<- survfit(fit.surv~group,data=survival)
ggsurvplot(km_2,pval=TRUE)

egfr_sur <- survival %>% merge(.,GDC_phenotype[! GDC_phenotype$EGFR %in%  c('none',''),],by.x ='sample',by.y='sampleID',all = F)

egfr_sur$group<- ifelse(egfr_sur$score < 0.02,1,2)

fit.surv <-Surv(egfr_sur$OS.time,egfr_sur$OS)
km_2<- survfit(fit.surv~group,data=egfr_sur)
ggsurvplot(km_2,pval=TRUE)

survival$group<- ifelse((survival$score < 0.021), 1,2)

fit.surv <-Surv(survival$OS.time,survival$OS)
km_2<- survfit(fit.surv~group,data=survival)

p <- ggsurvplot(km_2, main = "Survival curve",
           conf.int = TRUE,# 可信区间
           palette = "npg",# 支持ggsci配色，自定义颜色，brewer palettes中的配色，等
           ggtheme = theme_classic(), # 支持ggplot2及其扩展包的主题
           legend.title = "Score",#改变图例名称
           legend.labs = c("Low", "High"),
           risk.table = TRUE,        # 增加risk table
           #risk.table.title = "Risk set sizes",
           ncensor.plot = TRUE, #增加删失事件表
           surv.median.line = "hv",
           pval=TRUE,  #添加P值
           log.rank.weights = "1", #pval.method
)
p

Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”
Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”
Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”
Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”

#https://github.com/kassambara/survminer/issues/152

# add method to grid.draw
grid.draw.ggsurvplot <- function(x){
  survminer:::print.ggsurvplot(x, newpage = FALSE)
}
# Remember to pass object `p`.
ggsave(
  filename ='survplot_TCGA_LUSC_byScore2.pdf',
  plot = p,
  device = 'pdf',
  #path = 'data/output',
  width = 8,
  height = 10
)

Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”
Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”
Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”

getwd()

ggsave(
  filename ='survplot_TCGA_LUSC_byScore2.pdf',
  plot = p,
  device = 'pdf',
  #path = 'data/output',
  width = 8,
  height = 11
)

Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”
Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”
Warning message in geom_segment(aes(x = 0, y = max(y2), xend = max(x1), yend = max(y2)), :
“All aesthetics have length 1, but the data has 2 rows.
ℹ Did you mean to use `annotate()`?”

	ID	Description	GeneRatio	BgRatio	pvalue	p.adjust	qvalue	geneID	Count
	<chr>	<chr>	<chr>	<chr>	<dbl>	<dbl>	<dbl>	<chr>	<int>
GO:0000280	GO:0000280	nuclear division	11/58	441/18870	8.497327e-08	0.0001724108	0.0001122542	7314/27338/5902/983/891/4605/811/1063/7153/10403/10051	11
GO:0048285	GO:0048285	organelle fission	11/58	488/18870	2.349718e-07	0.0002383788	0.0001552050	7314/27338/5902/983/891/4605/811/1063/7153/10403/10051	11
GO:0009410	GO:0009410	response to xenobiotic stimulus	10/58	434/18870	7.265422e-07	0.0003730989	0.0002429193	595/2947/1728/8061/983/218/5111/1499/811/1063	10
GO:0045787	GO:0045787	positive regulation of cell cycle	9/58	334/18870	7.603798e-07	0.0003730989	0.0002429193	595/8061/7027/5902/983/891/811/10403/10051	9
GO:0048144	GO:0048144	fibroblast proliferation	6/58	107/18870	9.194157e-07	0.0003730989	0.0002429193	2335/5052/1163/983/891/1499	6
GO:0140014	GO:0140014	mitotic nuclear division	8/58	274/18870	1.824414e-06	0.0006169560	0.0004016911	27338/5902/983/891/4605/1063/10403/10051	8
GO:0000302	GO:0000302	response to reactive oxygen species	7/58	205/18870	3.031463e-06	0.0008786912	0.0005721032	5052/1728/8061/8878/10105/983/5111	7
GO:0000819	GO:0000819	sister chromatid segregation	7/58	225/18870	5.598675e-06	0.0014199639	0.0009245180	983/891/4605/1063/7153/10403/10051	7
GO:0034614	GO:0034614	cellular response to reactive oxygen species	6/58	154/18870	7.642157e-06	0.0016092253	0.0010477434	5052/1728/8878/10105/983/5111	6
GO:0044839	GO:0044839	cell cycle G2/M phase transition	6/58	155/18870	7.931125e-06	0.0016092253	0.0010477434	595/983/891/2305/1063/10403	6
GO:0033044	GO:0033044	regulation of chromosome organization	7/58	247/18870	1.029670e-05	0.0017884238	0.0011644169	983/891/1499/1063/7153/10403/10051	7
GO:0007292	GO:0007292	female gamete generation	6/58	163/18870	1.057717e-05	0.0017884238	0.0011644169	4192/7314/8061/1499/7153/10403	6
GO:0044772	GO:0044772	mitotic cell cycle phase transition	9/58	470/18870	1.231576e-05	0.0019133104	0.0012457288	595/27338/7027/1163/983/891/2305/1063/10403	9
GO:0010038	GO:0010038	response to metal ion	8/58	359/18870	1.327532e-05	0.0019133104	0.0012457288	1728/4502/3727/7846/10105/983/5111/811	8
GO:0042542	GO:0042542	response to hydrogen peroxide	5/58	101/18870	1.454701e-05	0.0019133104	0.0012457288	1728/8061/10105/983/5111	5
GO:0090068	GO:0090068	positive regulation of cell cycle process	7/58	262/18870	1.508771e-05	0.0019133104	0.0012457288	595/7027/5902/983/891/10403/10051	7
GO:0000070	GO:0000070	mitotic sister chromatid segregation	6/58	184/18870	2.105023e-05	0.0024196270	0.0015753843	983/891/4605/1063/10403/10051	6
GO:0051402	GO:0051402	neuron apoptotic process	7/58	278/18870	2.209923e-05	0.0024196270	0.0015753843	595/4192/1728/7314/7846/4605/1499	7
GO:0033047	GO:0033047	regulation of mitotic sister chromatid segregation	4/58	54/18870	2.265792e-05	0.0024196270	0.0015753843	983/891/1063/10403	4
GO:0031099	GO:0031099	regeneration	6/58	191/18870	2.598302e-05	0.0026359771	0.0017162466	595/928/4192/975/983/5111	6
GO:0071248	GO:0071248	cellular response to metal ion	6/58	200/18870	3.365097e-05	0.0032498273	0.0021159157	1728/4502/3727/7846/10105/811	6
GO:0051383	GO:0051383	kinetochore organization	3/58	21/18870	3.523716e-05	0.0032498273	0.0021159157	1063/10403/10051	3
GO:0007059	GO:0007059	chromosome segregation	8/58	424/18870	4.360081e-05	0.0038463500	0.0025043030	55839/983/891/4605/1063/7153/10403/10051	8
GO:0098813	GO:0098813	nuclear chromosome segregation	7/58	312/18870	4.610380e-05	0.0038976922	0.0025377312	983/891/4605/1063/7153/10403/10051	7
GO:0051983	GO:0051983	regulation of chromosome segregation	5/58	131/18870	5.095420e-05	0.0041354431	0.0026925273	983/891/1063/10403/10051	5
GO:0070301	GO:0070301	cellular response to hydrogen peroxide	4/58	67/18870	5.330706e-05	0.0041600010	0.0027085167	1728/10105/983/5111	4
GO:1905448	GO:1905448	positive regulation of mitochondrial ATP synthesis coupled electron transport	2/58	4/18870	5.548980e-05	0.0041699556	0.0027149980	983/891	2
GO:0007098	GO:0007098	centrosome cycle	5/58	138/18870	6.528838e-05	0.0046997710	0.0030599531	7846/5902/983/1499/10403	5
GO:0000086	GO:0000086	G2/M transition of mitotic cell cycle	5/58	140/18870	6.990543e-05	0.0046997710	0.0030599531	595/983/891/2305/1063	5
GO:0071241	GO:0071241	cellular response to inorganic substance	6/58	229/18870	7.149451e-05	0.0046997710	0.0030599531	1728/4502/3727/7846/10105/811	6
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
GO:0043010	GO:0043010	camera-type eye development	1/58	344/18870	0.6565542	0.6660743	0.4336713	1499	1
GO:0034249	GO:0034249	negative regulation of amide metabolic process	1/58	345/18870	0.6576295	0.6668317	0.4341645	811	1
GO:0071496	GO:0071496	cellular response to external stimulus	1/58	346/18870	0.6587014	0.6675850	0.4346549	8061	1
GO:0032496	GO:0032496	response to lipopolysaccharide	1/58	348/18870	0.6608354	0.6694134	0.4358454	1728	1
GO:0045862	GO:0045862	positive regulation of proteolysis	1/58	350/18870	0.6629562	0.6708919	0.4368080	302	1
GO:0051235	GO:0051235	maintenance of location	1/58	350/18870	0.6629562	0.6708919	0.4368080	811	1
GO:0070588	GO:0070588	calcium ion transmembrane transport	1/58	352/18870	0.6650640	0.6726894	0.4379784	302	1
GO:0030522	GO:0030522	intracellular receptor signaling pathway	1/58	353/18870	0.6661131	0.6734148	0.4384507	811	1
GO:0090287	GO:0090287	regulation of cellular response to growth factor stimulus	1/58	357/18870	0.6702771	0.6772870	0.4409718	1499	1
GO:0009100	GO:0009100	glycoprotein metabolic process	1/58	370/18870	0.6834607	0.6899213	0.4491978	1499	1
GO:0032535	GO:0032535	regulation of cellular component size	1/58	370/18870	0.6834607	0.6899213	0.4491978	2335	1
GO:1901653	GO:1901653	cellular response to peptide	1/58	374/18870	0.6874120	0.6935649	0.4515701	5315	1
GO:0002460	GO:0002460	adaptive immune response based on somatic recombination of immune receptors built from immunoglobulin superfamily domains	1/58	380/18870	0.6932482	0.6991056	0.4551776	975	1
GO:0001654	GO:0001654	eye development	1/58	391/18870	0.7036710	0.7092640	0.4617916	1499	1
GO:0150063	GO:0150063	visual system development	1/58	395/18870	0.7073742	0.7126426	0.4639913	1499	1
GO:0031331	GO:0031331	positive regulation of cellular catabolic process	1/58	396/18870	0.7082928	0.7132140	0.4643633	8878	1
GO:0010959	GO:0010959	regulation of metal ion transport	1/58	398/18870	0.7101217	0.7147008	0.4653314	1499	1
GO:0048880	GO:0048880	sensory system development	1/58	401/18870	0.7128438	0.7170848	0.4668836	1499	1
GO:0003002	GO:0003002	regionalization	1/58	430/18870	0.7378958	0.7415506	0.4828129	1499	1
GO:0043434	GO:0043434	response to peptide hormone	1/58	430/18870	0.7378958	0.7415506	0.4828129	5315	1
GO:0042391	GO:0042391	regulation of membrane potential	1/58	440/18870	0.7460261	0.7493500	0.4878910	7314	1
GO:0007409	GO:0007409	axonogenesis	1/58	448/18870	0.7523514	0.7553296	0.4917842	2335	1
GO:0006869	GO:0006869	lipid transport	1/58	453/18870	0.7562259	0.7588439	0.4940723	302	1
GO:0034765	GO:0034765	regulation of monoatomic ion transmembrane transport	1/58	454/18870	0.7569936	0.7592387	0.4943294	10105	1
GO:0007015	GO:0007015	actin filament organization	1/58	464/18870	0.7645412	0.7664299	0.4990114	800	1
GO:0007389	GO:0007389	pattern specification process	1/58	475/18870	0.7725776	0.7741036	0.5040077	1499	1
GO:0023061	GO:0023061	signal release	1/58	484/18870	0.7789518	0.7801052	0.5079152	7052	1
GO:0050804	GO:0050804	modulation of chemical synaptic transmission	1/58	489/18870	0.7824168	0.7831888	0.5099229	8878	1
GO:0099177	GO:0099177	regulation of trans-synaptic signaling	1/58	490/18870	0.7831033	0.7834895	0.5101187	8878	1
GO:0031667	GO:0031667	response to nutrient levels	1/58	495/18870	0.7865044	0.7865044	0.5120817	1728	1

	ID	Description	Count	GeneRatio	geneID
	<chr>	<chr>	<int>	<chr>	<chr>
GO:0000003	GO:0000003	reproduction	29	29/59	KRT8/KRT8/CD9/CD9/CD9/MDK/UBB/UBB/FOSL1/FOSL1/FOSL1/FOSL1/CDK1/CDK1/CDK1/CDK1/PCNA/CTNNB1/CTNNB1/CTNNB1/CALR/CALR/TOP2A/NDC80/NDC80/SMC4/SMC4/SMC4/SMC4
GO:0002376	GO:0002376	immune system process	33	33/59	FN1/FN1/FN1/FN1/FN1/FN1/CD9/CD9/CD9/MDK/PRDX1/NQO1/NQO1/FOSL1/FOSL1/FOSL1/FOSL1/SQSTM1/CD24/CD24/CD24/CD81/CD81/CD81/LAMP1/LAMP1/PPP1R14B/TUBB4B/CTNNB1/CTNNB1/CTNNB1/CALR/CALR
GO:0008152	GO:0008152	metabolic process	100	100/59	FN1/FN1/FN1/FN1/FN1/FN1/CCND1/CCND1/GSTM3/GSTM3/MDK/PRDX1/PGK1/PGK1/NQO1/NQO1/ALPP/ALPP/PKM/PKM/PKM/PKM/UBB/UBB/FOSL1/FOSL1/FOSL1/FOSL1/CTSA/CTSA/CTSA/CTSA/UBE2S/HSPB1/HSPB1/TCOF1/TCOF1/TCOF1/TFDP1/TFDP1/CSTB/CSTB/JUND/TGM2/TGM2/TGM2/TGM2/SQSTM1/CKS1B/CKS1B/CD24/CD24/CD24/LDHB/LDHB/TUBA1A/HMGA1/HMGA1/CD81/CD81/CD81/PPIF/PPIF/PSMB6/PSMB6/PSMB6/CDK1/CDK1/CDK1/CDK1/CCNB1/SERPINH1/SERPINH1/SERPINH1/FOXM1/FOXM1/FOXM1/FOXM1/PPP1R14B/ALDH3A1/ALDH3A1/ALDH3A1/IGFBP3/IGFBP3/MYBL2/PHGDH/UBC/PCNA/CTNNB1/CTNNB1/CTNNB1/CALR/CALR/MCM3/MCM3/MCM3/CENPF/ANXA2/ANXA2/TOP2A
GO:0009987	GO:0009987	cellular process	120	120/59	FN1/FN1/FN1/FN1/FN1/FN1/CCND1/CCND1/KRT8/KRT8/GSTM3/GSTM3/CD9/CD9/CD9/MDK/PRDX1/PGK1/PGK1/NQO1/NQO1/ALPP/ALPP/MT2A/PKM/PKM/PKM/PKM/UBB/UBB/FOSL1/FOSL1/FOSL1/FOSL1/CTSA/CTSA/CTSA/CTSA/UBE2S/HSPB1/HSPB1/MYL6/TCOF1/TCOF1/TCOF1/TFDP1/TFDP1/JUND/TGM2/TGM2/TGM2/TGM2/SQSTM1/CKS1B/CKS1B/CD24/CD24/CD24/LDHB/LDHB/TUBA1A/RANBP1/RANBP1/RANBP1/RANBP1/RANBP1/CENPN/HMGA1/HMGA1/CD81/CD81/CD81/PPIF/PPIF/CDK1/CDK1/CDK1/CDK1/CCNB1/SERPINH1/SERPINH1/SERPINH1/FOXM1/FOXM1/FOXM1/FOXM1/LAMP1/LAMP1/PPP1R14B/TFPI2/ALDH3A1/ALDH3A1/ALDH3A1/CALD1/CALD1/TUBA4A/IGFBP3/IGFBP3/TUBB4B/MYBL2/PHGDH/PCNA/CTNNB1/CTNNB1/CTNNB1/CALR/CALR/MCM3/MCM3/MCM3/CENPF/ANXA2/ANXA2/TOP2A/NDC80/NDC80/SMC4/SMC4/SMC4/SMC4
GO:0016032	GO:0016032	viral process	10	10/59	CD81/CD81/CD81/CDK1/CDK1/CDK1/CDK1/LAMP1/LAMP1/TOP2A
GO:0022414	GO:0022414	reproductive process	29	29/59	KRT8/KRT8/CD9/CD9/CD9/MDK/UBB/UBB/FOSL1/FOSL1/FOSL1/FOSL1/CDK1/CDK1/CDK1/CDK1/PCNA/CTNNB1/CTNNB1/CTNNB1/CALR/CALR/TOP2A/NDC80/NDC80/SMC4/SMC4/SMC4/SMC4
GO:0032501	GO:0032501	multicellular organismal process	78	78/59	FN1/FN1/FN1/FN1/FN1/FN1/CCND1/CCND1/KRT8/KRT8/GSTM3/GSTM3/CD9/CD9/CD9/MDK/PRDX1/PGK1/PGK1/PKM/PKM/PKM/PKM/UBB/UBB/FOSL1/FOSL1/FOSL1/FOSL1/HSPB1/HSPB1/MYL6/TCOF1/TCOF1/TCOF1/CSTB/CSTB/JUND/TGM2/TGM2/TGM2/TGM2/SQSTM1/CD24/CD24/CD24/TUBA1A/CD81/CD81/CD81/CDK1/CDK1/CDK1/CDK1/CCNB1/SERPINH1/SERPINH1/SERPINH1/LAMP1/LAMP1/TFPI2/CALD1/CALD1/IGFBP3/IGFBP3/PHGDH/PCNA/CTNNB1/CTNNB1/CTNNB1/CALR/CALR/CENPF/ANXA2/ANXA2/TOP2A/NDC80/NDC80
GO:0032502	GO:0032502	developmental process	73	73/59	FN1/FN1/FN1/FN1/FN1/FN1/CCND1/CCND1/KRT8/KRT8/GSTM3/GSTM3/CD9/CD9/CD9/MDK/PRDX1/PGK1/PGK1/PKM/PKM/PKM/PKM/UBB/UBB/FOSL1/FOSL1/FOSL1/FOSL1/HSPB1/HSPB1/MYL6/TCOF1/TCOF1/TCOF1/TFDP1/TFDP1/JUND/TGM2/TGM2/TGM2/TGM2/SQSTM1/CD24/CD24/CD24/TUBA1A/CD81/CD81/CD81/CDK1/CDK1/CDK1/CDK1/CCNB1/SERPINH1/SERPINH1/SERPINH1/CALD1/CALD1/IGFBP3/IGFBP3/PHGDH/PCNA/CTNNB1/CTNNB1/CTNNB1/CALR/CALR/CENPF/ANXA2/ANXA2/TOP2A
GO:0040007	GO:0040007	growth	23	23/59	FN1/FN1/FN1/FN1/FN1/FN1/CD9/CD9/CD9/MDK/MT2A/CD81/CD81/CD81/CDK1/CDK1/CDK1/CDK1/IGFBP3/IGFBP3/CTNNB1/CTNNB1/CTNNB1
GO:0040011	GO:0040011	locomotion	23	23/59	FN1/FN1/FN1/FN1/FN1/FN1/CD9/CD9/CD9/MDK/FOSL1/FOSL1/FOSL1/FOSL1/HSPB1/HSPB1/CD81/CD81/CD81/IGFBP3/IGFBP3/CALR/CALR
GO:0042592	GO:0042592	homeostatic process	23	23/59	PRDX1/NQO1/NQO1/MT2A/UBB/UBB/UBE2S/HSPB1/HSPB1/TGM2/TGM2/TGM2/TGM2/SQSTM1/CD24/CD24/CD24/TUBA1A/CTNNB1/CTNNB1/CTNNB1/CALR/CALR
GO:0043473	GO:0043473	pigmentation	0	0/59
GO:0044419	GO:0044419	biological process involved in interspecies interaction between organisms	33	33/59	FN1/FN1/FN1/FN1/FN1/FN1/KRT8/KRT8/PRDX1/NQO1/NQO1/FOSL1/FOSL1/FOSL1/FOSL1/HSPB1/HSPB1/CD24/CD24/CD24/CD81/CD81/CD81/CDK1/CDK1/CDK1/CDK1/LAMP1/LAMP1/PPP1R14B/TUBB4B/CALR/CALR
GO:0044848	GO:0044848	biological phase	3	3/59	CTNNB1/CTNNB1/CTNNB1
GO:0048511	GO:0048511	rhythmic process	7	7/59	MDK/CDK1/CDK1/CDK1/CDK1/PCNA/TOP2A
GO:0048518	GO:0048518	positive regulation of biological process	74	74/59	FN1/FN1/FN1/FN1/FN1/FN1/CCND1/CCND1/MDK/NQO1/NQO1/PKM/PKM/PKM/PKM/UBB/UBB/FOSL1/FOSL1/FOSL1/FOSL1/UBE2S/HSPB1/HSPB1/TFDP1/TFDP1/JUND/TGM2/TGM2/TGM2/TGM2/SQSTM1/CD24/CD24/CD24/RANBP1/RANBP1/RANBP1/RANBP1/RANBP1/HMGA1/HMGA1/CD81/CD81/CD81/CDK1/CDK1/CDK1/CDK1/CCNB1/FOXM1/FOXM1/FOXM1/FOXM1/LAMP1/LAMP1/IGFBP3/IGFBP3/MYBL2/PCNA/CTNNB1/CTNNB1/CTNNB1/CALR/CALR/ANXA2/ANXA2/TOP2A/NDC80/NDC80/SMC4/SMC4/SMC4/SMC4
GO:0048519	GO:0048519	negative regulation of biological process	66	66/59	FN1/FN1/FN1/FN1/FN1/FN1/CCND1/CCND1/CD9/CD9/CD9/MDK/PGK1/PGK1/NQO1/NQO1/MT2A/FOSL1/FOSL1/FOSL1/FOSL1/CTSA/CTSA/CTSA/CTSA/HSPB1/HSPB1/TFDP1/TFDP1/CSTB/CSTB/JUND/SQSTM1/CD24/CD24/CD24/HMGA1/HMGA1/PPIF/PPIF/CDK1/CDK1/CDK1/CDK1/CCNB1/SERPINH1/SERPINH1/SERPINH1/FOXM1/FOXM1/FOXM1/FOXM1/IGFBP3/IGFBP3/PCNA/CTNNB1/CTNNB1/CTNNB1/CALR/CALR/CENPF/ANXA2/ANXA2/TOP2A/NDC80/NDC80
GO:0050789	GO:0050789	regulation of biological process	106	106/59	FN1/FN1/FN1/FN1/FN1/FN1/CCND1/CCND1/KRT8/KRT8/CD9/CD9/CD9/MDK/PRDX1/PGK1/PGK1/NQO1/NQO1/MT2A/PKM/PKM/PKM/PKM/UBB/UBB/FOSL1/FOSL1/FOSL1/FOSL1/CTSA/CTSA/CTSA/CTSA/UBE2S/HSPB1/HSPB1/TCOF1/TCOF1/TCOF1/TFDP1/TFDP1/CSTB/CSTB/JUND/TGM2/TGM2/TGM2/TGM2/SQSTM1/CKS1B/CKS1B/CD24/CD24/CD24/TUBA1A/RANBP1/RANBP1/RANBP1/RANBP1/RANBP1/HMGA1/HMGA1/CD81/CD81/CD81/PPIF/PPIF/CDK1/CDK1/CDK1/CDK1/CCNB1/SERPINH1/SERPINH1/SERPINH1/FOXM1/FOXM1/FOXM1/FOXM1/LAMP1/LAMP1/PPP1R14B/IGFBP3/IGFBP3/MYBL2/PHGDH/PCNA/CTNNB1/CTNNB1/CTNNB1/CALR/CALR/MCM3/MCM3/MCM3/CENPF/ANXA2/ANXA2/TOP2A/NDC80/NDC80/SMC4/SMC4/SMC4/SMC4
GO:0050896	GO:0050896	response to stimulus	94	94/59	FN1/FN1/FN1/FN1/FN1/FN1/CCND1/CCND1/KRT8/KRT8/GSTM3/GSTM3/CD9/CD9/CD9/MDK/PRDX1/PGK1/PGK1/NQO1/NQO1/MT2A/PKM/PKM/PKM/PKM/UBB/UBB/FOSL1/FOSL1/FOSL1/FOSL1/HSPB1/HSPB1/JUND/TGM2/TGM2/TGM2/TGM2/SQSTM1/CD24/CD24/CD24/TUBA1A/RANBP1/RANBP1/RANBP1/RANBP1/RANBP1/HMGA1/HMGA1/CD81/CD81/CD81/PPIF/PPIF/CDK1/CDK1/CDK1/CDK1/CCNB1/SERPINH1/SERPINH1/SERPINH1/FOXM1/FOXM1/FOXM1/FOXM1/LAMP1/LAMP1/PPP1R14B/TFPI2/ALDH3A1/ALDH3A1/ALDH3A1/IGFBP3/IGFBP3/TUBB4B/MYBL2/PCNA/CTNNB1/CTNNB1/CTNNB1/CALR/CALR/MCM3/MCM3/MCM3/CENPF/ANXA2/ANXA2/TOP2A/NDC80/NDC80
GO:0051179	GO:0051179	localization	49	49/59	CCND1/CCND1/CD9/CD9/CD9/UBB/UBB/CTSA/CTSA/CTSA/CTSA/HSPB1/HSPB1/TGM2/TGM2/TGM2/TGM2/SQSTM1/CD24/CD24/CD24/TUBA1A/RANBP1/RANBP1/RANBP1/RANBP1/RANBP1/CD81/CD81/CD81/PPIF/PPIF/CDK1/CDK1/CDK1/CDK1/CCNB1/LAMP1/LAMP1/CTNNB1/CTNNB1/CTNNB1/CALR/CALR/CENPF/ANXA2/ANXA2/NDC80/NDC80
GO:0051703	GO:0051703	biological process involved in intraspecies interaction between organisms	0	0/59
GO:0065007	GO:0065007	biological regulation	107	107/59	FN1/FN1/FN1/FN1/FN1/FN1/CCND1/CCND1/KRT8/KRT8/CD9/CD9/CD9/MDK/PRDX1/PGK1/PGK1/NQO1/NQO1/MT2A/PKM/PKM/PKM/PKM/UBB/UBB/FOSL1/FOSL1/FOSL1/FOSL1/CTSA/CTSA/CTSA/CTSA/UBE2S/HSPB1/HSPB1/TCOF1/TCOF1/TCOF1/TFDP1/TFDP1/CSTB/CSTB/JUND/TGM2/TGM2/TGM2/TGM2/SQSTM1/CKS1B/CKS1B/CD24/CD24/CD24/TUBA1A/RANBP1/RANBP1/RANBP1/RANBP1/RANBP1/HMGA1/HMGA1/CD81/CD81/CD81/PPIF/PPIF/CDK1/CDK1/CDK1/CDK1/CCNB1/SERPINH1/SERPINH1/SERPINH1/FOXM1/FOXM1/FOXM1/FOXM1/LAMP1/LAMP1/PPP1R14B/TFPI2/IGFBP3/IGFBP3/MYBL2/PHGDH/PCNA/CTNNB1/CTNNB1/CTNNB1/CALR/CALR/MCM3/MCM3/MCM3/CENPF/ANXA2/ANXA2/TOP2A/NDC80/NDC80/SMC4/SMC4/SMC4/SMC4
GO:0098754	GO:0098754	detoxification	6	6/59	GSTM3/GSTM3/PRDX1/NQO1/NQO1/MT2A

	ID	Description	setSize	enrichmentScore	NES	pvalue	p.adjust	qvalue	rank	leading_edge	core_enrichment
	<chr>	<chr>	<int>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<chr>	<chr>
GO:0000819	GO:0000819	sister chromatid segregation	7	-0.7685950	-1.907089	0.000695424	0.3074144	0.3074144	36	tags=100%, list=28%, signal=81%	983/983/983/983/7153/4605/1063/10403/10403/10051/10051/10051/10051
GO:0033044	GO:0033044	regulation of chromosome organization	7	-0.7685950	-1.907089	0.000695424	0.3074144	0.3074144	36	tags=100%, list=28%, signal=82%	983/983/983/983/7153/1063/10403/10403/10051/10051/10051/10051/1499/1499/1499
GO:0098813	GO:0098813	nuclear chromosome segregation	7	-0.7685950	-1.907089	0.000695424	0.3074144	0.3074144	36	tags=100%, list=28%, signal=81%	983/983/983/983/7153/4605/1063/10403/10403/10051/10051/10051/10051
GO:0000070	GO:0000070	mitotic sister chromatid segregation	6	-0.7622951	-1.858672	0.002765156	0.3074144	0.3074144	36	tags=100%, list=28%, signal=80%	983/983/983/983/4605/1063/10403/10403/10051/10051/10051/10051
GO:0051276	GO:0051276	chromosome organization	12	-0.5603448	-1.786687	0.004917357	0.3074144	0.3074144	64	tags=96%, list=50%, signal=59%	3159/3159/891/983/983/983/983/5111/7153/4605/1063/10403/10403/10051/10051/10051/10051/4172/4172/4172/1499/1499/1499
GO:0051983	GO:0051983	regulation of chromosome segregation	5	-0.7560976	-1.749891	0.007103453	0.3074144	0.3074144	36	tags=100%, list=28%, signal=79%	983/983/983/983/1063/10403/10403/10051/10051/10051/10051
GO:0051383	GO:0051383	kinetochore organization	3	-0.8960000	-1.685244	0.006260319	0.3074144	0.3074144	17	tags=100%, list=13%, signal=92%	10403/10403/10051/10051/10051/10051
GO:0006281	GO:0006281	DNA repair	4	-0.7580645	-1.631976	0.036172583	0.3074144	0.3074144	35	tags=100%, list=27%, signal=80%	983/983/983/2305/2305/2305/2305/5111/4172/4172/4172
GO:0010638	GO:0010638	positive regulation of organelle organization	4	-0.7580645	-1.631976	0.036172583	0.3074144	0.3074144	35	tags=100%, list=27%, signal=81%	983/983/983/10051/10051/10051/10051/302/302/1499/1499/1499
GO:0051054	GO:0051054	positive regulation of DNA metabolic process	4	-0.7580645	-1.631976	0.036172583	0.3074144	0.3074144	35	tags=100%, list=27%, signal=80%	983/983/983/2305/2305/2305/2305/5111/1499/1499/1499
GO:0033045	GO:0033045	regulation of sister chromatid segregation	4	-0.7500000	-1.614615	0.041190693	0.3074144	0.3074144	36	tags=100%, list=28%, signal=77%	983/983/983/983/1063/10403/10403
GO:0033047	GO:0033047	regulation of mitotic sister chromatid segregation	4	-0.7500000	-1.614615	0.041190693	0.3074144	0.3074144	36	tags=100%, list=28%, signal=77%	983/983/983/983/1063/10403/10403
GO:0051304	GO:0051304	chromosome separation	4	-0.7500000	-1.614615	0.041190693	0.3074144	0.3074144	36	tags=88%, list=28%, signal=67%	1063/10403/10403/10051/10051/10051/10051
GO:0051783	GO:0051783	regulation of nuclear division	4	-0.7500000	-1.614615	0.041190693	0.3074144	0.3074144	36	tags=83%, list=28%, signal=63%	811/811/1063/10403/10403
GO:1902850	GO:1902850	microtubule cytoskeleton organization involved in mitosis	4	-0.7500000	-1.614615	0.041190693	0.3074144	0.3074144	36	tags=100%, list=28%, signal=77%	983/983/983/983/4605/10403/10403
GO:1905818	GO:1905818	regulation of chromosome separation	4	-0.7500000	-1.614615	0.041190693	0.3074144	0.3074144	36	tags=88%, list=28%, signal=67%	1063/10403/10403/10051/10051/10051/10051
GO:2001251	GO:2001251	negative regulation of chromosome organization	4	-0.7500000	-1.614615	0.041190693	0.3074144	0.3074144	36	tags=100%, list=28%, signal=75%	7153/1063/10403/10403
GO:0060537	GO:0060537	muscle tissue development	5	0.8577866	1.592443	0.005939521	0.3074144	0.3074144	1	tags=9%, list=1%, signal=10%	4637
GO:0007517	GO:0007517	muscle organ development	3	0.9576972	1.590136	0.001401771	0.3074144	0.3074144	1	tags=20%, list=1%, signal=21%	4637
GO:0033002	GO:0033002	muscle cell proliferation	4	-0.7338710	-1.579892	0.055052347	0.3074144	0.3074144	38	tags=100%, list=30%, signal=77%	3486/983/983/983/983/10403/10403/1499/1499/1499
GO:0051129	GO:0051129	negative regulation of cellular component organization	6	-0.6475410	-1.578872	0.019173190	0.3074144	0.3074144	50	tags=100%, list=39%, signal=66%	10105/891/7153/1063/10403/10403/302/302
GO:0050767	GO:0050767	regulation of neurogenesis	5	0.8441406	1.567110	0.007819628	0.3074144	0.3074144	20	tags=69%, list=16%, signal=66%	2335/2335/2335/2335/2335/2335/7052/7052/7052/7052/4192
GO:0051960	GO:0051960	regulation of nervous system development	5	0.8441406	1.567110	0.007819628	0.3074144	0.3074144	20	tags=69%, list=16%, signal=66%	2335/2335/2335/2335/2335/2335/7052/7052/7052/7052/4192
GO:0060284	GO:0060284	regulation of cell development	5	0.8441406	1.567110	0.007819628	0.3074144	0.3074144	20	tags=69%, list=16%, signal=66%	2335/2335/2335/2335/2335/2335/7052/7052/7052/7052/4192
GO:0097237	GO:0097237	cellular response to toxic substance	3	0.9280000	1.540828	0.007792079	0.3074144	0.3074144	12	tags=100%, list=9%, signal=94%	1728/1728/2947/2947/5052
GO:1990748	GO:1990748	cellular detoxification	3	0.9280000	1.540828	0.007792079	0.3074144	0.3074144	12	tags=100%, list=9%, signal=94%	1728/1728/2947/2947/5052
GO:0006816	GO:0006816	calcium ion transport	2	-0.9523810	-1.538281	0.011460554	0.3074144	0.3074144	9	tags=100%, list=7%, signal=97%	302/1499/1499/1499
GO:0030001	GO:0030001	metal ion transport	2	-0.9523810	-1.538281	0.011460554	0.3074144	0.3074144	9	tags=100%, list=7%, signal=97%	302/1499/1499/1499
GO:0007507	GO:0007507	heart development	5	0.8231498	1.528141	0.014170618	0.3074144	0.3074144	7	tags=38%, list=5%, signal=41%	2335/2335/2335/2335/2335/2335
GO:0010720	GO:0010720	positive regulation of cell development	4	0.8552063	1.502433	0.016048778	0.3074144	0.3074144	20	tags=79%, list=16%, signal=74%	2335/2335/2335/2335/2335/2335/7052/7052/7052/7052/4192
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
GO:0051052	GO:0051052	regulation of DNA metabolic process	6	0.3126659	0.5994505	0.9595051	0.9907572	0.9907572	94	tags=88%, list=73%, signal=27%	983/983/983/983/2305/2305/2305/2305/5111/4172/4172/4172/1499/1499/1499
GO:0097435	GO:0097435	supramolecular fiber organization	5	0.3188595	0.5919485	0.9690011	0.9907572	0.9907572	29	tags=20%, list=23%, signal=17%	3856/3856
GO:0031323	GO:0031323	regulation of cellular metabolic process	30	0.2383703	0.5824553	0.9790210	0.9907572	0.9907572	65	tags=51%, list=51%, signal=54%	2335/2335/2335/2335/2335/2335/4192/8061/8061/8061/8061/5476/5476/5476/5476/7027/7027/8878/100133941/100133941/100133941/975/975/975/1163/1163/5315/5315/5315/5315/595/595/6949/6949/6949
GO:0009968	GO:0009968	negative regulation of signal transduction	7	0.2924752	0.5824015	0.9695652	0.9907572	0.9907572	61	tags=94%, list=48%, signal=56%	3315/3315/10105/10105/3486/3486/2305/2305/2305/2305/811/811/1499/1499/1499
GO:0010648	GO:0010648	negative regulation of cell communication	7	0.2924752	0.5824015	0.9695652	0.9907572	0.9907572	61	tags=94%, list=48%, signal=56%	3315/3315/10105/10105/3486/3486/2305/2305/2305/2305/811/811/1499/1499/1499
GO:0023057	GO:0023057	negative regulation of signaling	7	0.2924752	0.5824015	0.9695652	0.9907572	0.9907572	61	tags=94%, list=48%, signal=56%	3315/3315/10105/10105/3486/3486/2305/2305/2305/2305/811/811/1499/1499/1499
GO:0051172	GO:0051172	negative regulation of nitrogen compound metabolic process	16	0.2548207	0.5814103	0.9696049	0.9907572	0.9907572	43	tags=26%, list=34%, signal=24%	1728/1728/5476/5476/5476/5476/1476/1476/8878
GO:0051726	GO:0051726	regulation of cell cycle	14	0.2562795	0.5745464	0.9675127	0.9907572	0.9907572	62	tags=41%, list=48%, signal=29%	8061/8061/8061/8061/7027/7027/5902/5902/5902/5902/5902/1163/1163/595/595
GO:0031324	GO:0031324	negative regulation of cellular metabolic process	17	0.2572748	0.5912486	0.9827060	0.9910678	0.9910678	7	tags=14%, list=5%, signal=20%	2335/2335/2335/2335/2335/2335
GO:0006360	GO:0006360	transcription by RNA polymerase I	1	0.5118110	0.6827330	0.9860558	0.9924354	0.9924354	65	tags=100%, list=51%, signal=50%	6949/6949/6949
GO:0009303	GO:0009303	rRNA transcription	1	0.5118110	0.6827330	0.9860558	0.9924354	0.9924354	65	tags=100%, list=51%, signal=50%	6949/6949/6949
GO:0014029	GO:0014029	neural crest formation	1	0.5118110	0.6827330	0.9860558	0.9924354	0.9924354	65	tags=100%, list=51%, signal=50%	6949/6949/6949
GO:0016072	GO:0016072	rRNA metabolic process	1	0.5118110	0.6827330	0.9860558	0.9924354	0.9924354	65	tags=100%, list=51%, signal=50%	6949/6949/6949
GO:0042790	GO:0042790	nucleolar large rRNA transcription by RNA polymerase I	1	0.5118110	0.6827330	0.9860558	0.9924354	0.9924354	65	tags=100%, list=51%, signal=50%	6949/6949/6949
GO:0007005	GO:0007005	mitochondrion organization	2	0.3809524	0.5766925	0.9881657	0.9936230	0.9936230	81	tags=100%, list=63%, signal=38%	8878/10105/10105
GO:0010821	GO:0010821	regulation of mitochondrion organization	2	0.3809524	0.5766925	0.9881657	0.9936230	0.9936230	81	tags=100%, list=63%, signal=38%	8878/10105/10105
GO:0006357	GO:0006357	regulation of transcription by RNA polymerase II	15	0.2273327	0.5134139	0.9888325	0.9936230	0.9936230	62	tags=36%, list=48%, signal=25%	8061/8061/8061/8061/7027/7027/8878/975/975/975/595/595
GO:0006366	GO:0006366	transcription by RNA polymerase II	15	0.2273327	0.5134139	0.9888325	0.9936230	0.9936230	62	tags=36%, list=48%, signal=25%	8061/8061/8061/8061/7027/7027/8878/975/975/975/595/595
GO:0031055	GO:0031055	chromatin remodeling at centromere	1	-0.5118110	-0.6713375	0.9900000	0.9938969	0.9938969	64	tags=100%, list=50%, signal=50%
GO:0034080	GO:0034080	CENP-A containing chromatin assembly	1	-0.5118110	-0.6713375	0.9900000	0.9938969	0.9938969	64	tags=100%, list=50%, signal=50%
GO:0044092	GO:0044092	negative regulation of molecular function	4	0.3145161	0.5525443	0.9903030	0.9938969	0.9938969	91	tags=100%, list=71%, signal=31%	1476/1476/3315/3315/10105/10105/871/871/871
GO:0043086	GO:0043086	negative regulation of catalytic activity	3	0.3120000	0.5180370	0.9960988	0.9973977	0.9973977	91	tags=100%, list=71%, signal=31%	1476/1476/3315/3315/871/871/871
GO:0045931	GO:0045931	positive regulation of mitotic cell cycle	4	0.2873663	0.5048472	0.9963636	0.9973977	0.9973977	94	tags=100%, list=73%, signal=29%	7027/595/595/891/983/983/983/983
GO:1901989	GO:1901989	positive regulation of cell cycle phase transition	4	0.2873663	0.5048472	0.9963636	0.9973977	0.9973977	94	tags=100%, list=73%, signal=29%	7027/595/595/891/983/983/983/983
GO:1901992	GO:1901992	positive regulation of mitotic cell cycle phase transition	4	0.2873663	0.5048472	0.9963636	0.9973977	0.9973977	94	tags=100%, list=73%, signal=29%	7027/595/595/891/983/983/983/983
GO:0000280	GO:0000280	nuclear division	11	0.2212110	0.4790455	0.9948347	0.9973977	0.9973977	68	tags=33%, list=53%, signal=19%	27338/5902/5902/5902/5902/5902/7314/7314
GO:0048285	GO:0048285	organelle fission	11	0.2212110	0.4790455	0.9948347	0.9973977	0.9973977	68	tags=33%, list=53%, signal=19%	27338/5902/5902/5902/5902/5902/7314/7314
GO:0007049	GO:0007049	cell cycle	25	0.2000446	0.4778260	0.9969970	0.9973977	0.9973977	74	tags=41%, list=58%, signal=29%	27338/8061/8061/8061/8061/7027/7027/5902/5902/5902/5902/5902/1163/1163/595/595/55839/7314/7314/3727/7846
GO:0000278	GO:0000278	mitotic cell cycle	18	0.1943552	0.4484935	0.9969666	0.9973977	0.9973977	62	tags=31%, list=48%, signal=23%	27338/7027/7027/5902/5902/5902/5902/5902/1163/1163/595/595
GO:0022402	GO:0022402	cell cycle process	21	0.1944509	0.4559383	0.9989940	0.9989940	0.9989940	68	tags=34%, list=53%, signal=24%	27338/7027/7027/5902/5902/5902/5902/5902/1163/1163/595/595/55839/7314/7314

V1	is_tf	is_in_FAM	is_in_ROS	is_in_Pathway	weight_shap_total	weight_shap_total_dir	weight_shap_0	weight_shap_0_dir	weight_shap_1	⋯	weight_grad_0	weight_grad_0_dir	weight_grad_1	weight_grad_1_dir	is_driver_shap_total	is_driver_shap_0	is_driver_shap_1	is_driver_grad_total	is_driver_grad_0	is_driver_grad_1
<chr>	<lgl>	<lgl>	<lgl>	<lgl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	⋯	<dbl>	<dbl>	<dbl>	<dbl>	<lgl>	<lgl>	<lgl>	<lgl>	<lgl>	<lgl>
H2AFZ	FALSE	TRUE	FALSE	TRUE	0.001396736	-4.011072e-05	0.001240849	0.001474716	0.001561170	⋯	0.001331874	6.733973e-11	0.0008687093	4.257443e-09	TRUE	TRUE	TRUE	TRUE	TRUE	TRUE
PRDX1	FALSE	FALSE	TRUE	TRUE	0.005420250	-4.785569e-04	0.005700868	-0.009741519	0.005124247	⋯	0.002573374	1.301101e-10	0.0026004973	1.291586e-08	TRUE	TRUE	TRUE	TRUE	TRUE	TRUE
NQO1	FALSE	FALSE	TRUE	TRUE	0.007288831	-1.938082e-04	0.007157244	-0.012187278	0.007427631	⋯	0.003293566	1.665231e-10	0.0031686146	1.573753e-08	TRUE	TRUE	TRUE	TRUE	TRUE	TRUE

	category	subcategory	ID	Description	GeneRatio	BgRatio	pvalue	p.adjust	qvalue	geneID	Count
	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<dbl>	<dbl>	<dbl>	<chr>	<int>
hsa05208	Human Diseases	Cancer: overview	hsa05208	Chemical carcinogenesis - reactive oxygen species	4/72	331/11008	0.1707392	0.2815419	0.1926339	P21266/Q6FGJ9/P15559/P30405	4

t0_14¶

t7_14¶

t14 cyc_ncyc¶

t0_cyc_ncyc¶

build pip¶

add new func¶

ext lung¶

sen¶

SEN¶

load GDSC¶

load CCLE¶

pipe¶

read data¶

test single gene¶

GDSC¶

CCLE¶

test sorce¶

GDSC¶

CCLE¶

add chord plot¶

survival¶

gs_name	entrez_gene
<chr>	<int>
HALLMARK_ADIPOGENESIS	19
HALLMARK_ADIPOGENESIS	11194
HALLMARK_ADIPOGENESIS	10449
HALLMARK_ADIPOGENESIS	33
HALLMARK_ADIPOGENESIS	34
HALLMARK_ADIPOGENESIS	35

1	2	3	4	5	6	7	8	9	10
4.724133	5.491294	4.535267	4.495636	4.495066	5.532322	4.567998	5.963493	5.827968	4.496718
5.960347	5.513097	4.495066	5.232386	5.040282	5.135537	4.718235	5.319920	4.515816	4.496024
5.690746	4.928036	5.272539	4.495066	4.495538	4.495066	5.866435	4.855198	5.963629	5.291622
4.495067	5.513097	4.495066	4.495066	5.931807	5.657654	5.191741	5.963048	4.941186	5.918016
5.935060	4.621886	5.961474	5.706913	4.551802	5.865337	5.904000	5.768884	4.577091	4.495066
5.317416	5.531489	4.957732	5.963507	5.895158	5.802080	4.495066	5.042022	5.963575	5.880892
5.660109	4.495066	5.958095	4.631964	4.511030	4.495074	5.897695	4.495066	5.126250	5.901836
5.367441	5.549653	5.960465	4.885332	5.919073	4.508134	4.495066	4.495068	5.403415	5.522206
4.495067	5.652659	5.319215	5.957193	5.583002	4.495067	5.569531	5.955827	4.815738	5.390085
4.528517	5.015393	5.955680	5.933313	5.652573	5.597127	5.823828	4.568487	4.495067	4.495071

	weight_shap_total_mean	gs
	<dbl>	<chr>
72	1.284743e-03	HALLMARK_TGF_BETA_SIGNALING
171	9.876715e-04	HALLMARK_TGF_BETA_SIGNALING
261	1.945853e-03	HALLMARK_CHOLESTEROL_HOMEOSTASIS
31	5.934694e-05	HALLMARK_CHOLESTEROL_HOMEOSTASIS
102	5.009635e-04	HALLMARK_COAGULATION
33	5.934694e-05	HALLMARK_COAGULATION
24	1.806040e-03	HALLMARK_EPITHELIAL_MESENCHYMAL_TRANSITION
232	8.014264e-04	HALLMARK_EPITHELIAL_MESENCHYMAL_TRANSITION
221	8.638531e-04	HALLMARK_G2M_CHECKPOINT
1	5.255194e-04	HALLMARK_G2M_CHECKPOINT
233	8.014264e-04	HALLMARK_HYPOXIA
103	5.009635e-04	HALLMARK_HYPOXIA
251	2.708228e-04	HALLMARK_KRAS_SIGNALING_UP
14	1.475505e-04	HALLMARK_KRAS_SIGNALING_UP
262	1.945853e-03	HALLMARK_P53_PATHWAY
131	7.297564e-04	HALLMARK_P53_PATHWAY
34	5.934694e-05	HALLMARK_IL6_JAK_STAT3_SIGNALING
263	1.945853e-03	HALLMARK_PI3K_AKT_MTOR_SIGNALING
6	1.071527e-04	HALLMARK_DNA_REPAIR
281	4.270763e-04	HALLMARK_UV_RESPONSE_UP
282	4.270763e-04	HALLMARK_MITOTIC_SPINDLE
192	2.453577e-03	HALLMARK_ADIPOGENESIS
104	5.009635e-04	HALLMARK_COMPLEMENT
11	5.255194e-04	HALLMARK_E2F_TARGETS
152	9.237856e-04	HALLMARK_GLYCOLYSIS
5	1.481077e-03	HALLMARK_HEME_METABOLISM
12	5.255194e-04	HALLMARK_KRAS_SIGNALING_DN
8	1.301767e-03	HALLMARK_MYOGENESIS
193	2.453577e-03	HALLMARK_XENOBIOTIC_METABOLISM

	weight_shap_total_mean	gs
	<dbl>	<chr>
110	5.943084e-04	Notch Signaling
42	2.135133e-04	Notch Signaling
82	8.007617e-05	Hedgehog Signaling
21	1.053465e-04	Pancreas Beta Cells
163	1.167002e-03	Reactive Oxygen Species Pathway
335	2.943991e-04	Myc Targets V2
6	3.319458e-04	Heme Metabolism
211	1.053465e-04	Heme Metabolism
143	1.767575e-03	Kras Signaling Up
194	3.295498e-04	Kras Signaling Up
125	6.298396e-04	Il6 Jak Stat3 Signaling
361	3.769688e-04	Peroxisome
61	3.319458e-04	Coagulation
351	2.753436e-04	Uv Response Dn
352	2.753436e-04	Apical Junction
62	3.319458e-04	Complement
144	1.767575e-03	Glycolysis
312	5.431046e-04	Inflammatory Response
313	5.431046e-04	Interferon Gamma Response
242	1.453233e-03	Myc Targets V1

SLC1A5	COSMIC_ID
7.975696	908460
8.479559	908465
7.921446	910399
8.292501	687816
8.027455	724873
6.631435	722045
7.023257	724868
6.888380	724866
7.311690	687798
7.524080	908475
7.615405	908463
7.948984	753608
6.803541	910931
6.233322	1240202
6.868018	908472
5.548601	910900
6.404932	687799
7.906778	722058
5.958910	753600
7.294597	1298348
7.409463	1240185
7.990055	908476
7.260682	1298350
8.770801	907786
6.959397	753592
6.980728	906805
6.845378	724859
7.646560	905949
6.658691	1240146
7.316419	909721
⋮	⋮
6.277130	905972
7.823917	905970
7.501640	1240145
7.221498	1290908
6.656378	1503370
7.991184	1247873
8.246154	906791
4.751698	1503369
6.452249	687820
6.779306	908473
7.837235	687800
7.370621	687821
7.476429	905967
5.368187	687807
7.382293	1240187
6.394580	722066
6.565660	724874
7.994473	1240190
6.296948	687802
7.003254	687812
7.360163	687819
5.701877	905942
5.595287	905944
6.619834	924244
7.869154	713869
9.138640	1298347
8.486290	1298537
7.738085	687777
7.078411	724834
7.740654	722046

	Erlotinib	Lapatinib	Osimertinib	ZD-6474
ANXA2	-0.36716625	-0.54191262	0.004082954	-0.36989069
BARD1	0.15849550	0.18913780	-0.097575263	-0.05995084
CD9	-0.27811604	-0.37724916	-0.088261276	-0.29266084
CEBPD	0.01206895	0.04715317	-0.106193334	-0.16106570
DAAM1	-0.40778755	-0.44904895	-0.518766520	-0.30115493
DGKE	0.04380999	-0.01012269	0.115840427	-0.14849669
GTF2B	-0.01651038	0.02642410	0.004675303	-0.15078139
HIST1H1C	-0.12555192	-0.10326080	0.092923887	-0.19222652
HSPA2	0.15927702	0.16280258	-0.012426096	-0.19581700
KLF5	-0.20706362	-0.34800671	-0.308475948	-0.11558346
LMO7	-0.29777327	-0.26518112	0.095621202	-0.11126481
MSH6	0.10830159	0.08294254	-0.041415908	0.12335927
MYO1B	-0.19706211	-0.31746279	-0.316363859	-0.10491314
PLK2	-0.23060607	-0.34227929	-0.098415166	-0.34928249
PSMC4	0.13138846	0.02879852	0.170478791	-0.10556595
RAB31	0.26435422	0.30693390	-0.054640531	0.10907555
RRBP1	-0.39072017	-0.46196864	-0.155403122	-0.25853461
SLC1A5	0.12595750	0.07289740	0.100480841	0.19855327
TFAP2C	-0.19239185	-0.30826752	-0.165888109	-0.30572149
TFDP1	-0.43256213	-0.20295966	0.138099376	-0.22291079
TGM2	-0.05314013	-0.15071512	-0.014999345	-0.21722184
TPM1	0.05509583	0.01603657	0.138427871	-0.26174438
TRIB1	-0.19656845	-0.21971159	0.001650178	0.02471996
TUBA1B	0.14186892	0.20743117	0.163705070	-0.08908780
TUBB4B	-0.36231141	-0.26564096	-0.080657379	-0.23206919

	Erlotinib	Lapatinib	Osimertinib	ZD-6474
ANXA2	0.04216628	0.001639199	9.750867e-01	0.04054861
BARD1	0.39443438	0.308186572	4.543944e-01	0.74869276
CD9	0.12979298	0.036427233	4.987845e-01	0.11010731
CEBPD	0.94862159	0.801126935	4.153328e-01	0.38671226
DAAM1	0.02277635	0.011275639	1.843256e-05	0.09969599
DGKE	0.81497566	0.956898558	3.739904e-01	0.42530412
GTF2B	0.92975418	0.887789647	9.714737e-01	0.41813530
HIST1H1C	0.50095518	0.580409490	4.762866e-01	0.30020616
HSPA2	0.39207702	0.381543662	9.242777e-01	0.29109490
KLF5	0.26370749	0.055054351	1.557443e-02	0.53580016
LMO7	0.10374793	0.149372696	4.635234e-01	0.55124632
MSH6	0.56196312	0.657337078	7.513098e-01	0.50852074
MYO1B	0.28797688	0.081813421	1.299438e-02	0.57433335
PLK2	0.21199387	0.059457365	4.505011e-01	0.05410956
PSMC4	0.48109570	0.877778585	1.889890e-01	0.57194067
RAB31	0.15069316	0.093049814	6.757715e-01	0.55915481
RRBP1	0.02976071	0.008888952	2.317320e-01	0.16022545
SLC1A5	0.49956199	0.696746838	4.410045e-01	0.28427088
TFAP2C	0.29978271	0.091565046	2.013561e-01	0.09441545
TFDP1	0.01508307	0.273499044	2.885206e-01	0.22806822
TGM2	0.77647654	0.418342261	9.086580e-01	0.24046724
TPM1	0.76846900	0.931765363	2.873641e-01	0.15491601
TRIB1	0.28921055	0.234986660	9.899296e-01	0.89498519
TUBA1B	0.44648053	0.262841871	2.074346e-01	0.63365707
TUBB4B	0.04517675	0.148642007	5.366215e-01	0.20902769

A data.table: 10 × 7
seed	shap_total	shap_0	shap_1	grad_total	grad_0	grad_1
<int>	<int>	<int>	<int>	<int>	<int>	<int>
0	25	25	25	22	24	23
1	24	26	25	23	24	24
2	24	23	25	20	24	18
3	24	25	25	25	24	25
4	24	24	26	22	20	23
5	24	24	26	20	24	18
6	24	24	24	22	24	23
7	24	24	26	22	26	23
8	22	23	23	23	25	24
9	23	23	25	23	23	24

A data.frame: 6 × 11
	category	subcategory	ID	Description	GeneRatio	BgRatio	pvalue	p.adjust	qvalue	geneID	Count
	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<dbl>	<dbl>	<dbl>	<chr>	<int>
hsa04218	Cellular Processes	Cell growth and death	hsa04218	Cellular senescence	7/49	156/8753	2.287756e-05	0.001716776	0.001392998	595/8878/983/891/2305/3486/4605	7
hsa04110	Cellular Processes	Cell growth and death	hsa04110	Cell cycle	7/49	157/8753	2.384412e-05	0.001716776	0.001392998	595/7027/983/891/5111/4172/10403	7
hsa00010	Metabolism	Carbohydrate metabolism	hsa00010	Glycolysis / Gluconeogenesis	4/49	67/8753	5.127849e-04	0.022663076	0.018388900	5230/5315/3945/218	4
hsa05012	Human Diseases	Neurodegenerative disease	hsa05012	Parkinson disease	7/49	266/8753	6.370286e-04	0.022663076	0.018388900	7314/7846/10105/5694/7277/10383/7316	7
hsa04115	Cellular Processes	Cell growth and death	hsa04115	p53 signaling pathway	4/49	75/8753	7.869124e-04	0.022663076	0.018388900	595/983/891/3486	4
hsa05022	Human Diseases	Neurodegenerative disease	hsa05022	Pathways of neurodegeneration - multiple diseases	9/49	476/8753	1.128896e-03	0.027093516	0.021983774	7314/8878/7846/10105/5694/7277/10383/7316/1499	9

A data.frame: 144 × 11
	category	subcategory	ID	Description	GeneRatio	BgRatio	pvalue	p.adjust	qvalue	geneID	Count
	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<dbl>	<dbl>	<dbl>	<chr>	<int>
hsa04218	Cellular Processes	Cell growth and death	hsa04218	Cellular senescence	7/49	156/8753	2.287756e-05	0.001716776	0.001392998	CCND1/SQSTM1/CDK1/CCNB1/FOXM1/IGFBP3/MYBL2	7
hsa04110	Cellular Processes	Cell growth and death	hsa04110	Cell cycle	7/49	157/8753	2.384412e-05	0.001716776	0.001392998	CCND1/TFDP1/CDK1/CCNB1/PCNA/MCM3/NDC80	7
hsa00010	Metabolism	Carbohydrate metabolism	hsa00010	Glycolysis / Gluconeogenesis	4/49	67/8753	5.127849e-04	0.022663076	0.018388900	PGK1/PKM/LDHB/ALDH3A1	4
hsa05012	Human Diseases	Neurodegenerative disease	hsa05012	Parkinson disease	7/49	266/8753	6.370286e-04	0.022663076	0.018388900	UBB/TUBA1A/PPIF/PSMB6/TUBA4A/TUBB4B/UBC	7
hsa04115	Cellular Processes	Cell growth and death	hsa04115	p53 signaling pathway	4/49	75/8753	7.869124e-04	0.022663076	0.018388900	CCND1/CDK1/CCNB1/IGFBP3	4
hsa05022	Human Diseases	Neurodegenerative disease	hsa05022	Pathways of neurodegeneration - multiple diseases	9/49	476/8753	1.128896e-03	0.027093516	0.021983774	UBB/SQSTM1/TUBA1A/PPIF/PSMB6/TUBA4A/TUBB4B/UBC/CTNNB1	9
hsa04540	Cellular Processes	Cellular community - eukaryotes	hsa04540	Gap junction	4/49	88/8753	1.431436e-03	0.027422076	0.022250369	TUBA1A/CDK1/TUBA4A/TUBB4B	4
hsa04145	Cellular Processes	Transport and catabolism	hsa04145	Phagosome	5/49	152/8753	1.523449e-03	0.027422076	0.022250369	TUBA1A/LAMP1/TUBA4A/TUBB4B/CALR	5
hsa04530	Cellular Processes	Cellular community - eukaryotes	hsa04530	Tight junction	5/49	170/8753	2.490451e-03	0.039847219	0.032332174	CCND1/MYL6/TUBA1A/TUBA4A/PCNA	5
hsa05016	Human Diseases	Neurodegenerative disease	hsa05016	Huntington disease	6/49	306/8753	6.856213e-03	0.097172299	0.078845944	TGM2/TUBA1A/PPIF/PSMB6/TUBA4A/TUBB4B	6
hsa05418	Human Diseases	Cardiovascular disease	hsa05418	Fluid shear stress and atherosclerosis	4/49	139/8753	7.422884e-03	0.097172299	0.078845944	GSTM3/NQO1/SQSTM1/CTNNB1	4
hsa01230	Metabolism	Global and overview maps	hsa01230	Biosynthesis of amino acids	3/49	75/8753	8.393387e-03	0.100720641	0.081725082	PGK1/PKM/PHGDH	3
hsa05132	Human Diseases	Infectious disease: bacterial	hsa05132	Salmonella infection	5/49	247/8753	1.191903e-02	0.129047398	0.104709512	TUBA1A/TUBA4A/TUBB4B/CTNNB1/ANXA2	5
hsa04140	Cellular Processes	Transport and catabolism	hsa04140	Autophagy - animal	4/49	165/8753	1.335173e-02	0.129047398	0.104709512	UBB/SQSTM1/LAMP1/UBC	4
hsa05225	Human Diseases	Cancer: specific types	hsa05225	Hepatocellular carcinoma	4/49	168/8753	1.418522e-02	0.129047398	0.104709512	CCND1/GSTM3/NQO1/CTNNB1	4
hsa05222	Human Diseases	Cancer: specific types	hsa05222	Small cell lung cancer	3/49	92/8753	1.461035e-02	0.129047398	0.104709512	FN1/CCND1/CKS1B	3
hsa03030	Genetic Information Processing	Replication and repair	hsa03030	DNA replication	2/49	36/8753	1.713450e-02	0.129047398	0.104709512	PCNA/MCM3	2
hsa05020	Human Diseases	Neurodegenerative disease	hsa05020	Prion disease	5/49	272/8753	1.746331e-02	0.129047398	0.104709512	TUBA1A/PPIF/PSMB6/TUBA4A/TUBB4B	5
hsa05216	Human Diseases	Cancer: specific types	hsa05216	Thyroid cancer	2/49	37/8753	1.804957e-02	0.129047398	0.104709512	CCND1/CTNNB1	2
hsa05146	Human Diseases	Infectious disease: parasitic	hsa05146	Amoebiasis	3/49	102/8753	1.921568e-02	0.129047398	0.104709512	FN1/PRDX1/HSPB1	3
hsa05010	Human Diseases	Neurodegenerative disease	hsa05010	Alzheimer disease	6/49	384/8753	1.947279e-02	0.129047398	0.104709512	TUBA1A/PPIF/PSMB6/TUBA4A/TUBB4B/CTNNB1	6
hsa04137	Cellular Processes	Transport and catabolism	hsa04137	Mitophagy - animal	3/49	103/8753	1.971557e-02	0.129047398	0.104709512	UBB/SQSTM1/UBC	3
hsa04814	Cellular Processes	Cell motility	hsa04814	Motor proteins	4/49	193/8753	2.243184e-02	0.136869617	0.111056488	MYL6/TUBA1A/TUBA4A/TUBB4B	4
hsa05167	Human Diseases	Infectious disease: viral	hsa05167	Kaposi sarcoma-associated herpesvirus infection	4/49	194/8753	2.281160e-02	0.136869617	0.111056488	CCND1/UBB/UBC/CTNNB1	4
hsa01200	Metabolism	Global and overview maps	hsa01200	Carbon metabolism	3/49	115/8753	2.627589e-02	0.148581769	0.120559769	PGK1/PKM/PHGDH	3
hsa05203	Human Diseases	Cancer: overview	hsa05203	Viral carcinogenesis	4/49	204/8753	2.682726e-02	0.148581769	0.120559769	CCND1/PKM/RANBP1/CDK1	4
hsa00620	Metabolism	Carbohydrate metabolism	hsa00620	Pyruvate metabolism	2/49	47/8753	2.827941e-02	0.150823516	0.122378730	PKM/LDHB	2
hsa00270	Metabolism	Amino acid metabolism	hsa00270	Cysteine and methionine metabolism	2/49	52/8753	3.408291e-02	0.174152303	0.141307790	LDHB/PHGDH	2
hsa05166	Human Diseases	Infectious disease: viral	hsa05166	Human T-cell leukemia virus 1 infection	4/49	222/8753	3.507234e-02	0.174152303	0.141307790	CCND1/FOSL1/RANBP1/CALR	4
hsa04142	Cellular Processes	Transport and catabolism	hsa04142	Lysosome	3/49	132/8753	3.734000e-02	0.179231989	0.145429464	LAPTM4A/CTSA/LAMP1	3
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
hsa01522	Human Diseases	Drug resistance: antineoplastic	hsa01522	Endocrine resistance	1/49	98/8753	0.4249125	0.5320644	0.4317189	CCND1	1
hsa04916	Organismal Systems	Endocrine system	hsa04916	Melanogenesis	1/49	101/8753	0.4346260	0.5388652	0.4372371	CTNNB1	1
hsa05142	Human Diseases	Infectious disease: parasitic	hsa05142	Chagas disease	1/49	102/8753	0.4378279	0.5388652	0.4372371	CALR	1
hsa04350	Environmental Information Processing	Signal transduction	hsa04350	TGF-beta signaling pathway	1/49	108/8753	0.4566700	0.5572921	0.4521888	TFDP1	1
hsa05145	Human Diseases	Infectious disease: parasitic	hsa05145	Toxoplasmosis	1/49	111/8753	0.4658576	0.5637268	0.4574099	PPIF	1
hsa04928	Organismal Systems	Endocrine system	hsa04928	Parathyroid hormone synthesis, secretion and action	1/49	114/8753	0.4748929	0.5687063	0.4614503	JUND	1
hsa04670	Organismal Systems	Immune system	hsa04670	Leukocyte transendothelial migration	1/49	115/8753	0.4778713	0.5687063	0.4614503	CTNNB1	1
hsa04935	Organismal Systems	Endocrine system	hsa04935	Growth hormone synthesis, secretion and action	1/49	120/8753	0.4925167	0.5799772	0.4705955	IGFBP3	1

A data.frame: 200 × 72
	HALLMARK_TNFA_SIGNALING_VIA_NFKB	HALLMARK_HYPOXIA	HALLMARK_CHOLESTEROL_HOMEOSTASIS	HALLMARK_TGF_BETA_SIGNALING	HALLMARK_DNA_REPAIR	HALLMARK_G2M_CHECKPOINT	HALLMARK_APOPTOSIS	HALLMARK_NOTCH_SIGNALING	HALLMARK_ADIPOGENESIS	HALLMARK_ESTROGEN_RESPONSE_EARLY	⋯	HALLMARK_IL2_STAT5_SIGNALING	HALLMARK_ALLOGRAFT_REJECTION	HALLMARK_KRAS_SIGNALING_UP	FATTY_ACID_BETA_OXIDATION	S.GENES.ITAY	G2M.GENES.ITAY	CELL_CYCLE	NRF2_ROMORO	KEGG_GLUTATHIONE_METABOLISM	GO_ANTIOXIDANT_ACTIVITY
	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	⋯	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>
1	JUNB	PGK1	FDPS	TGFBR1	POLR2H	AURKA	CASP3	JAG1	FABP4	GREB1	⋯	SOCS2	PTPRC	ANGPTL4	ACADM	MCM5	HMGB2	MCM5	TXNRD1	ANPEP	ALB
2	CXCL2	PDK1	CYP51A1	SMAD7	POLR2A	CCNA2	CASP9	NOTCH3	ADIPOQ	CA12	⋯	CISH	IL12B	ITGA2	ACADS	PCNA	CDK1	PCNA	TKT	G6PD	ALOX5AP
3	ATF3	GBE1	IDI1	TGFB1	POLR2G	TOP2A	DFFA	NOTCH2	PPARG	SLC9A3R1	⋯	PIM1	TGFB1	SPRY2	ACADVL	TYMS	NUSAP1	TYMS	SRXN1	GCLC	APOA4
4	NFKBIA	PFKL	FDFT1	SMURF2	POLR2E	CCNB2	CASP7	APH1A	LIPE	MYB	⋯	IL2RA	IL12A	HBEGF	BDH2	FEN1	UBE2C	FEN1	NQO1	GCLM	APOE
5	TNFAIP3	ALDOA	DHCR7	SMURF1	POLR2J	CENPA	CFLAR	HES1	DGAT1	ANXA9	⋯	TNFRSF4	CD3E	RBP4	CPT1A	MCM2	BIRC5	MCM2	GCLC	GGCT	APOM
6	PTGS2	ENO2	SQLE	BMPR2	POLR2F	BIRC5	BIRC3	CCND1	LPL	IGFBP4	⋯	SOCS1	CD3D	HSD11B1	CPT1B	MCM4	TPX2	MCM4	G6PD	GGT1	CAT
7	CXCL1	PGM1	HMGCS1	SKIL	POLR2C	CDC20	PMAIP1	FZD1	CPT2	SYBU	⋯	TNFRSF9	CD28	ETV4	ECH1	RRM1	TOP2A	RRM1	FTH1	GGT5	CCS
8	IER3	NDRG1	NSDHL	SKI	POLR2K	PLK1	CASP8	PSEN2	CD36	NPY1R	⋯	XBP1	LYN	GLRX	ECHS1	UNG	NDC80	UNG	EPHX1	GGT6	CLIC2
9	CD83	HK2	LSS	ACVR1	GTF2H3	TTK	JUN	FZD7	GPAM	PDZK1	⋯	RRAGD	HCLS1	DUSP6	HADHB	GINS2	CKS2	GINS2	DDC	GGT7	CYGB
10	CCL20	ALDOC	MVD	PMEPA1	POLR2D	PRC1	BCL2L11	DTX1	ADIPOR2	NRIP1	⋯	HK2	IL18	SCG5	PPARA	MCM6	NUF2	MCM6	CBR3	GPX1	DUOX1
11	CXCL3	GPI	LDLR	NCOR2	ERCC3	NDC80	MCL1	DLL1	ACAA2	MLPH	⋯	PHLDA1	CRTAM	ETV5	PPARD	CDCA7	CKS1B	CDCA7	UIP1	GPX2	DUOX2
12	MAFF	MXI1	TM7SF2	SERPINE1	DDB2	KIF11	IL1B	FZD5	ETFB	HSPB8	⋯	IL2RB	IFNG	ITGB2	CPT1C	DTL	MKI67	DTL	UCHL1	GPX3	EPX
13	NFKB2	SLC2A1	ALDOC	JUNB	POLR1C	NUSAP1	SPTAN1	MAML2	ACOX1	EGR3	⋯	CTLA4	CD3G	AKT2	NA	PRIM1	TMPO	PRIM1	TXN	GPX4	FABP1
14	TNFAIP2	P4HA1	EBP	SMAD1	XPC	CKS2	DIABLO	NOTCH1	ACADM	KRT19	⋯	NFIL3	CD86	PPBP	NA	UHRF1	CENPF	UHRF1	TSPAN7	GPX5	GPX1
15	HBEGF	ADM	SCD	SMAD6	PCNA	KIF2C	BAX	PSENEN	HADH	LRIG1	⋯	CD83	IL10	G0S2	NA	MLF1IP	TACC3	MLF1IP	TRIM16	GPX6	GPX2
16	KLF6	P4HA2	PMVK	PPP1R15A	POLR2I	MKI67	BIK	WNT5A	IDH1	KDM4B	⋯	IKZF2	UBE2N	GABRA3	NA	HELLS	FAM64A	HELLS	TM4SF20	GPX7	GPX3
17	BIRC3	ENO1	MVK	TGIF1	SUPT4H1	AURKB	IL1A	CUL1	SORBS1	PGR	⋯	IL10	BCL10	IRF8	NA	RFC2	SMC4	RFC2	TGFB2	GSR	GPX4
18	PLAUR	PFKP	LPL	FURIN	POLD3	TPX2	BID	WNT2	ACADS	RHOBTB3	⋯	TNFRSF18	CD4	BIRC3	NA	RPA2	CCNB2	RPA2	TFRC	GSS	GPX5
19	ZFP36	AK4	SC5D	SMAD3	POLR3GL	SMC4	CDKN1A	DTX4	UCK1	TPD52L1	⋯	DHRS3	LCK	FGF9	NA	NASP	CKAP2L	NASP	TALDO1	GSTA1	GPX6
20	ICAM1	FAM162A	FADS2	FKBP1A	POLR3C	BUB1	GADD45A	SAP30	SCP2	ELOVL2	⋯	ECM1	NCK1	DCBLD2	NA	RAD51AP1	CKAP2	RAD51AP1	SQSTM1	GSTA2	GPX7
21	JUN	PFKFB3	HMGCR	MAP3K7	GTF2B	CENPF	DDIT3	PPARD	DECR1	RET	⋯	ADAM19	C2	INHBA	NA	GMNN	AURKB	GMNN	SPP1	GSTA3	GPX8
22	EGR3	VEGFA	HSD17B7	BMPR1A	POLR1D	RACGAP1	CDKN1B	KAT2A	CDKN2C	TPBG	⋯	SLC2A3	HLA-A	TFPI	NA	WDR76	BUB1	WDR76	SPANXB1	GSTA4	GSR
23	IL1B	BNIP3L	ANXA13	CTNNB1	NCBP2	CENPE	TNF	HEYL	TALDO1	TFF1	⋯	HIPK2	ITGB2	TSPAN1	NA	SLBP	KIF11	SLBP	SPANXA1	GSTA5	GSTA1
24	BCL2A1	TPI1	SREBF2	HIPK2	NELFE	AC027237.1	GSN	SKP1	TST	MAPT	⋯	BATF3	HLA-DQA1	ADAM8	NA	CCNE2	ANP32E	CCNE2	SORD	GSTK1	GSTK1
25	PPP1R15A	ERO1A	PCYT2	KLF10	GTF2F1	UBE2C	TNFSF10	RBX1	MCCC1	SCNN1A	⋯	BHLHE40	CD1D	SLPI	NA	UBR7	TUBB4B	UBR7	SLC7A11	GSTM1	GSTM2
26	ZC3H12A	KDM3A	ACSS2	BMP2	ERCC5	MCM6	CASP6	TCF7L2	PGM1	ABAT	⋯	PTGER2	CD80	PRKG2	NA	POLD3	GTSE1	POLD3	SLC6A6	GSTM2	GSTO1
27	SOD2	CCNG2	ATF3	ENG	LIG1	MCM3	SQSTM1	ARRB1	REEP5	FLNB	⋯	DENND5A	HLA-DRA	MMP11	NA	MSH2	KIF20B	MSH2	SLC38A6	GSTM3	GSTO2
28	NR4A2	LDHA	ADH4	APC	ERCC1	PTTG1	FASLG	LFNG	BCL2L13	XBP1	⋯	ITIH5	THY1	MMP10	NA	ATAD2	HJURP	ATAD2	SFN	GSTM4	GSTP1
29	IL1A	GYS1	ETHE1	PPM1A	ERCC4	CDK1	EGR3	PRKCA	SLC25A10	CELSR2	⋯	PHTF2	TLR1	TMEM158	NA	RAD51	CDCA3	RAD51	SERPINE1	GSTM5	GSTT1
30	RELB	GAPDH	ECH1	XIAP	POLD4	KIF4A	CD44	DTX2	ME1	RAB31	⋯	GADD45B	HLA-G	TNFAIP3	NA	RRM2	HN1	RRM2	RRM2	GSTO1	GSTZ1
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋱	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
171	IL12B	MYH9	NA	NA	NA	HMGN2	NA	NA	DHRS7B	INHBB	⋯	UMPS	RIPK2	FUCA1	NA	NA	NA	NA	NA	NA	NA
172	IL6ST	CDKN1C	NA	NA	NA	SRSF10	NA	NA	MIGA2	BHLHE40	⋯	HUWE1	IKBKB	PLVAP	NA	NA	NA	NA	NA	NA	NA
173	SLC16A6	GRHPR	NA	NA	NA	SNRPD1	NA	NA	MGLL	CALB2	⋯	COL6A1	GCNT1	ADAM17	NA	NA	NA	NA	NA	NA	NA
174	ABCA1	PCK1	NA	NA	NA	CASP8AP2	NA	NA	ITSN1	FASN	⋯	ABCB1	SOCS5	AVL9	NA	NA	NA	NA	NA	NA	NA
175	HES1	INHA	NA	NA	NA	SMARCC1	NA	NA	DHCR7	CHPT1	⋯	RNH1	IRF8	ADAMDEC1	NA	NA	NA	NA	NA	NA	NA
176	BCL6	HSPA5	NA	NA	NA	SLC12A2	NA	NA	RREB1	MYBBP1A	⋯	IRF8	TAP2	HKDC1	NA	NA	NA	NA	NA	NA	NA
177	IRS2	NDST2	NA	NA	NA	NOTCH2	NA	NA	CMBL	ELOVL5	⋯	GUCY1B1	EIF4G3	MAP7	NA	NA	NA	NA	NA	NA	NA
178	SLC2A3	NEDD4L	NA	NA	NA	TNPO2	NA	NA	UBC	DYNLT3	⋯	AHCY	ABI1	IL7R	NA	NA	NA	NA	NA	NA	NA